#100 by GitHub stars
wanshuiyin/Auto-claude-code-research-in-sleep
ARIS ⚔<U+FE0F> (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/ablation-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/alphaxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/analyze-results/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/arxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/auto-paper-improvement-loop/SKILL.md
Week of Nov 2, 2026 · +5 / −2 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
- 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status
+ 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status, mcp__model-worker__worker, mcp__model-worker__worker_reply
- 18 > to reviewer-bearing children. Generation workers are unchanged.
+ 18 > to reviewer-bearing children. Writer selection is separate; follow the
+ 19 > writing-worker guidance below when drafting or revising prose.
+ 340 Follow the Launch Mindset and Optional Writing Worker guidance in `../shared-references/writing-principles.md`. For prose fixes, continue the configured writer with `worker_reply` (or start it with `worker`) under any active edit-whitelist constraints; otherwise revise directly. Pass the accepted fixes, source facts, and target files. Root checks technical accuracy while preserving strong prose; existing reviews, audits, and recompilation still apply.
+ 341
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/auto-review-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/auto-review-loop-llm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/auto-review-loop-minimax/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/citation-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/citation-crosscheck/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/claims-drafting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/comm-lit-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/deepxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/dse-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/embodiment-description/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/exa-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/experiment-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/experiment-bridge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/experiment-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/experiment-queue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/feishu-notify/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/figure-description/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/figure-spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/firecrawl-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/formula-derivation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/gemini-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/grant-proposal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/idea-creator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/idea-discovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/idea-discovery-robot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/integrity-forensics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/interview-cheatsheet/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/invention-structuring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/jurisdiction-format/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/keenable-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/kill-argument/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/lean-formalize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/mermaid-diagram/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/meta-apply/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/meta-optimize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/monitor-experiment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/novelty-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/openalex/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/overleaf-sync/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-claim-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-compile/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-figure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-illustration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-illustration-image2/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-plan/SKILL.md
Week of Nov 2, 2026 · +3 / −2 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
- 18 > to reviewer-bearing children. Generation workers are unchanged.
+ 18 > to reviewer-bearing children. Writer selection is separate; follow the
+ 19 > writing-worker guidance below when drafting or revising prose.
- 45 - Read `../shared-references/writing-principles.md` when framing the one-sentence contribution, Abstract, Introduction, Related Work, or hero figure.
+ 46 - Read `../shared-references/writing-principles.md` when framing the one-sentence contribution, Abstract, Introduction, Related Work, or hero figure. Plan the claims-evidence matrix under its Launch Mindset: lead with the strongest supported contribution, give each experiment an argumentative role, and bind assumptions to claims rather than building a disclaimer list.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-poster/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-poster-html/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-slides/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-talk/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-write/SKILL.md
Week of Nov 2, 2026 · +5 / −2 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
- 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status
+ 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status, mcp__model-worker__worker, mcp__model-worker__worker_reply
- 18 > to reviewer-bearing children. Generation workers are unchanged.
+ 18 > to reviewer-bearing children. Writer selection is separate; follow the
+ 19 > writing-worker guidance below when drafting or revising prose.
+ 217
+ 218 Use the Launch Mindset and Optional Writing Worker guidance in `../shared-references/writing-principles.md` for every section. Root prepares the factual brief from the plan, original sources, results, figures, and verified bibliography; a configured writer drafts substantive prose and handles same-session revisions, otherwise the executor writes. Pass any supplied `writer`, `writer-model`, and `writer-effort` independently of reviewer settings. Root checks technical accuracy and compilation while preserving the writer's good phrasing; the existing section reviews and audits still apply.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/paper-writing/SKILL.md
Week of Nov 2, 2026 · +7 / −4 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
- 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status
+ 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status, mcp__model-worker__worker, mcp__model-worker__worker_reply
- 18 > to reviewer-bearing children. Generation workers are unchanged.
+ 18 > to reviewer-bearing children. Writer selection is separate; follow the
+ 19 > writing-worker guidance below when drafting or revising prose.
+ 38
+ 39 Writer choice is independent of reviewer routing. Accept user/project preferences in natural language or `— writer: antigravity, writer-model: gemini-4-argon-high, writer-effort: high`; follow `../shared-references/writing-principles.md` for configured-worker use and executor fallback. Carry these writer options and any active writer session to `/paper-write` and the fix-implementation phase of `/auto-paper-improvement-loop`, separately from reviewer/model/effort overrides. Apply its Launch Mindset from planning through final revision.
- 388 Invoke `/paper-write` to generate section-by-section LaTeX:
+ 391 Invoke `/paper-write` to generate section-by-section LaTeX, forwarding any writer options:
- 491 Invoke `/auto-paper-improvement-loop` to polish the paper:
+ 494 Invoke `/auto-paper-improvement-loop` to polish the paper, forwarding the same writer options and available writer session for prose fixes:
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/patent-novelty-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/patent-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/patent-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/pixel-art/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/prior-art-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/proof-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/proof-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/proof-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/qzcli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/rebuttal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/render-html/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/research-implement-feature/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/research-lit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/research-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/research-refine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/research-refine-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/research-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/research-wiki/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/resubmit-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/result-to-claim/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/run-experiment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/semantic-scholar/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/serverless-modal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/auto-paper-improvement-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/auto-review-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/novelty-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/paper-figure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/paper-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/paper-write/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/research-refine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-claude-review/research-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/auto-paper-improvement-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/auto-review-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/grant-proposal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/idea-creator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/idea-discovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/idea-discovery-robot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/novelty-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/paper-figure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/paper-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/paper-poster-html/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/paper-slides/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/paper-write/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/paper-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/research-refine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex-gemini-review/research-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/ablation-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/alphaxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/analyze-results/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/arxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/auto-paper-improvement-loop/SKILL.md
Week of Nov 2, 2026 · +5 / −2 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
- 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status
+ 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status, mcp__model-worker__worker, mcp__model-worker__worker_reply
- 18 > to reviewer-bearing children. Generation workers are unchanged.
+ 18 > to reviewer-bearing children. Writer selection is separate; follow the
+ 19 > writing-worker guidance below when drafting or revising prose.
+ 285 Follow the Launch Mindset and Optional Writing Worker guidance in `../shared-references/writing-principles.md`. For prose fixes, continue the configured writer with `worker_reply` (or start it with `worker`) under any active edit-whitelist constraints; otherwise revise directly. Pass the accepted fixes, source facts, and target files. Root checks technical accuracy while preserving strong prose; existing reviews, audits, and recompilation still apply.
+ 286
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/auto-review-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/auto-review-loop-llm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/auto-review-loop-minimax/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/citation-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/citation-crosscheck/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/claims-drafting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/comm-lit-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/deepxiv/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/dse-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/embodiment-description/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/exa-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/experiment-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/experiment-bridge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/experiment-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/experiment-queue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/feishu-notify/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/figure-description/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/figure-spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/firecrawl-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/formula-derivation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/gemini-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/grant-proposal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/idea-creator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/idea-discovery/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/idea-discovery-robot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/integrity-forensics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/interview-cheatsheet/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/invention-structuring/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/jurisdiction-format/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/keenable-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/kill-argument/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/lean-formalize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/mermaid-diagram/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/meta-apply/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/meta-optimize/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/monitor-experiment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/novelty-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/openalex/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/overleaf-sync/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-claim-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-compile/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-figure/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-illustration/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-illustration-image2/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-plan/SKILL.md
Week of Nov 2, 2026 · +3 / −2 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
- 16 > to reviewer-bearing children. Generation workers are unchanged.
+ 16 > to reviewer-bearing children. Writer selection is separate; follow the
+ 17 > writing-worker guidance below when drafting or revising prose.
- 43 - Read `../shared-references/writing-principles.md` when framing the Abstract, Introduction, Related Work, or hero figure
+ 44 - Read `../shared-references/writing-principles.md` when framing the Abstract, Introduction, Related Work, or hero figure. Plan the claims-evidence matrix under its Launch Mindset: lead with the strongest supported contribution, give each experiment an argumentative role, and bind assumptions to claims rather than building a disclaimer list.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-poster/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-poster-html/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-slides/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-talk/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-write/SKILL.md
Week of Nov 2, 2026 · +4 / −1 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
- 16 > to reviewer-bearing children. Generation workers are unchanged.
+ 16 > to reviewer-bearing children. Writer selection is separate; follow the
+ 17 > writing-worker guidance below when drafting or revising prose.
+ 150
+ 151 Use the Launch Mindset and Optional Writing Worker guidance in `../shared-references/writing-principles.md` for every section. Root prepares the factual brief from the plan, original sources, results, figures, and verified bibliography; a configured writer drafts substantive prose and handles same-session revisions, otherwise the executor writes. Pass any supplied `writer`, `writer-model`, and `writer-effort` independently of reviewer settings. Root checks technical accuracy and compilation while preserving the writer's good phrasing; the existing section reviews and audits still apply.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/paper-writing/SKILL.md
Week of Nov 2, 2026 · +7 / −4 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
- 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status
+ 5 allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status, mcp__model-worker__worker, mcp__model-worker__worker_reply
- 18 > to reviewer-bearing children. Generation workers are unchanged.
+ 18 > to reviewer-bearing children. Writer selection is separate; follow the
+ 19 > writing-worker guidance below when drafting or revising prose.
+ 44
+ 45 Writer choice is independent of reviewer routing. Accept user/project preferences in natural language or `— writer: antigravity, writer-model: gemini-4-argon-high, writer-effort: high`; follow `../shared-references/writing-principles.md` for configured-worker use and executor fallback. Carry these writer options and any active writer session to `/paper-write` and the fix-implementation phase of `/auto-paper-improvement-loop`, separately from reviewer/model/effort overrides. Apply its Launch Mindset from planning through final revision.
- 286 Invoke `/paper-write` to generate section-by-section LaTeX:
+ 289 Invoke `/paper-write` to generate section-by-section LaTeX, forwarding any writer options:
- 387 Invoke `/auto-paper-improvement-loop` to polish the paper:
+ 390 Invoke `/auto-paper-improvement-loop` to polish the paper, forwarding the same writer options and available writer session for prose fixes:
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/patent-novelty-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/patent-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/patent-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/pixel-art/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/prior-art-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/proof-checker/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/proof-orchestrator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/proof-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/qzcli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/rebuttal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/render-html/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/research-implement-feature/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/research-lit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/research-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/research-refine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/research-refine-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/research-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/research-wiki/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/resubmit-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/result-to-claim/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/run-experiment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/semantic-scholar/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/serverless-modal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/slides-polish/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/specification-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/system-profile/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/training-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/vast-gpu/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/web-debug-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/wiki-enrich/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/skills-codex/writing-systems-papers/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/slides-polish/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/specification-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/system-profile/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/training-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/vast-gpu/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/web-debug-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/wiki-enrich/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
skills/writing-systems-papers/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a4f093dcf6f → 2901234ad295
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a4f093dcf6f
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 2901234ad2954cd2388ced8d3aed2ed9de42803a
git clone --filter=blob:none --no-checkout https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git .hotskills/wanshuiyin-auto-claude-code-research-in-sleep && git -C .hotskills/wanshuiyin-auto-claude-code-research-in-sleep checkout --detach 2901234ad2954cd2388ced8d3aed2ed9de42803a
# Copy each selected skill directory from .hotskills/wanshuiyin-auto-claude-code-research-in-sleep into .claude/skills/<skill-name>/18.8kGitHub stars
441stars in 7 days
197skills in this repository
81commits in 30 days
Heat
7.9- Star growth, last 7 daysAhead of 93% of tracked repositories
- Star growth, last 24 hoursAhead of 92% of tracked repositories
- Rank movement, last 7 daysAhead of 83% of tracked repositories
- Commits, last 30 daysAhead of 93% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- ablation-planner
skills/ablation-planner - alphaxiv
skills/alphaxiv - analyze-results
skills/analyze-results - arxiv
skills/arxiv - auto-paper-improvement-loop
skills/auto-paper-improvement-loop - auto-review-loop
skills/auto-review-loop - auto-review-loop-llm
skills/auto-review-loop-llm - auto-review-loop-minimax
skills/auto-review-loop-minimax - citation-audit
skills/citation-audit - citation-crosscheck
skills/citation-crosscheck - claims-drafting
skills/claims-drafting - comm-lit-review
skills/comm-lit-review - deepxiv
skills/deepxiv - dse-loop
skills/dse-loop - embodiment-description
skills/embodiment-description - exa-search
skills/exa-search - experiment-audit
skills/experiment-audit - experiment-bridge
skills/experiment-bridge - experiment-plan
skills/experiment-plan - experiment-queue
skills/experiment-queue - feishu-notify
skills/feishu-notify - figure-description
skills/figure-description - figure-spec
skills/figure-spec - firecrawl-search
skills/firecrawl-search - formula-derivation
skills/formula-derivation - gemini-search
skills/gemini-search - grant-proposal
skills/grant-proposal - idea-creator
skills/idea-creator - idea-discovery
skills/idea-discovery - idea-discovery-robot
skills/idea-discovery-robot - integrity-forensics
skills/integrity-forensics - interview-cheatsheet
skills/interview-cheatsheet - invention-structuring
skills/invention-structuring - jurisdiction-format
skills/jurisdiction-format - keenable-search
skills/keenable-search - kill-argument
skills/kill-argument - lean-formalize
skills/lean-formalize - mermaid-diagram
skills/mermaid-diagram - meta-apply
skills/meta-apply - meta-optimize
skills/meta-optimize - monitor-experiment
skills/monitor-experiment - novelty-check
skills/novelty-check - openalex
skills/openalex - overleaf-sync
skills/overleaf-sync - paper-claim-audit
skills/paper-claim-audit - paper-compile
skills/paper-compile - paper-figure
skills/paper-figure - paper-illustration
skills/paper-illustration - paper-illustration-image2
skills/paper-illustration-image2 - paper-plan
skills/paper-plan - paper-poster
skills/paper-poster - paper-poster-html
skills/paper-poster-html - paper-slides
skills/paper-slides - paper-talk
skills/paper-talk - paper-write
skills/paper-write - paper-writing
skills/paper-writing - patent-novelty-check
skills/patent-novelty-check - patent-pipeline
skills/patent-pipeline - patent-review
skills/patent-review - pixel-art
skills/pixel-art - prior-art-search
skills/prior-art-search - proof-checker
skills/proof-checker - proof-orchestrator
skills/proof-orchestrator - proof-writer
skills/proof-writer - qzcli
skills/qzcli - rebuttal
skills/rebuttal - render-html
skills/render-html - research-implement-feature
skills/research-implement-feature - research-lit
skills/research-lit - research-pipeline
skills/research-pipeline - research-refine
skills/research-refine - research-refine-pipeline
skills/research-refine-pipeline - research-review
skills/research-review - research-wiki
skills/research-wiki - resubmit-pipeline
skills/resubmit-pipeline - result-to-claim
skills/result-to-claim - run-experiment
skills/run-experiment - semantic-scholar
skills/semantic-scholar - serverless-modal
skills/serverless-modal - auto-paper-improvement-loop
skills/skills-codex-claude-review/auto-paper-improvement-loop - auto-review-loop
skills/skills-codex-claude-review/auto-review-loop - novelty-check
skills/skills-codex-claude-review/novelty-check - paper-figure
skills/skills-codex-claude-review/paper-figure - paper-plan
skills/skills-codex-claude-review/paper-plan - paper-write
skills/skills-codex-claude-review/paper-write - research-refine
skills/skills-codex-claude-review/research-refine - research-review
skills/skills-codex-claude-review/research-review - auto-paper-improvement-loop
skills/skills-codex-gemini-review/auto-paper-improvement-loop - auto-review-loop
skills/skills-codex-gemini-review/auto-review-loop - grant-proposal
skills/skills-codex-gemini-review/grant-proposal - idea-creator
skills/skills-codex-gemini-review/idea-creator - idea-discovery
skills/skills-codex-gemini-review/idea-discovery - idea-discovery-robot
skills/skills-codex-gemini-review/idea-discovery-robot - novelty-check
skills/skills-codex-gemini-review/novelty-check - paper-figure
skills/skills-codex-gemini-review/paper-figure - paper-plan
skills/skills-codex-gemini-review/paper-plan - paper-poster-html
skills/skills-codex-gemini-review/paper-poster-html - paper-slides
skills/skills-codex-gemini-review/paper-slides - paper-write
skills/skills-codex-gemini-review/paper-write - paper-writing
skills/skills-codex-gemini-review/paper-writing - research-refine
skills/skills-codex-gemini-review/research-refine - research-review
skills/skills-codex-gemini-review/research-review - ablation-planner
skills/skills-codex/ablation-planner - alphaxiv
skills/skills-codex/alphaxiv - analyze-results
skills/skills-codex/analyze-results - arxiv
skills/skills-codex/arxiv - auto-paper-improvement-loop
skills/skills-codex/auto-paper-improvement-loop - auto-review-loop
skills/skills-codex/auto-review-loop - auto-review-loop-llm
skills/skills-codex/auto-review-loop-llm - auto-review-loop-minimax
skills/skills-codex/auto-review-loop-minimax - citation-audit
skills/skills-codex/citation-audit - citation-crosscheck
skills/skills-codex/citation-crosscheck - claims-drafting
skills/skills-codex/claims-drafting - comm-lit-review
skills/skills-codex/comm-lit-review - deepxiv
skills/skills-codex/deepxiv - dse-loop
skills/skills-codex/dse-loop - embodiment-description
skills/skills-codex/embodiment-description - exa-search
skills/skills-codex/exa-search - experiment-audit
skills/skills-codex/experiment-audit - experiment-bridge
skills/skills-codex/experiment-bridge - experiment-plan
skills/skills-codex/experiment-plan - experiment-queue
skills/skills-codex/experiment-queue - feishu-notify
skills/skills-codex/feishu-notify - figure-description
skills/skills-codex/figure-description - figure-spec
skills/skills-codex/figure-spec - firecrawl-search
skills/skills-codex/firecrawl-search - formula-derivation
skills/skills-codex/formula-derivation - gemini-search
skills/skills-codex/gemini-search - grant-proposal
skills/skills-codex/grant-proposal - idea-creator
skills/skills-codex/idea-creator - idea-discovery
skills/skills-codex/idea-discovery - idea-discovery-robot
skills/skills-codex/idea-discovery-robot - integrity-forensics
skills/skills-codex/integrity-forensics - interview-cheatsheet
skills/skills-codex/interview-cheatsheet - invention-structuring
skills/skills-codex/invention-structuring - jurisdiction-format
skills/skills-codex/jurisdiction-format - keenable-search
skills/skills-codex/keenable-search - kill-argument
skills/skills-codex/kill-argument - lean-formalize
skills/skills-codex/lean-formalize - mermaid-diagram
skills/skills-codex/mermaid-diagram - meta-apply
skills/skills-codex/meta-apply - meta-optimize
skills/skills-codex/meta-optimize - monitor-experiment
skills/skills-codex/monitor-experiment - novelty-check
skills/skills-codex/novelty-check - openalex
skills/skills-codex/openalex - overleaf-sync
skills/skills-codex/overleaf-sync - paper-claim-audit
skills/skills-codex/paper-claim-audit - paper-compile
skills/skills-codex/paper-compile - paper-figure
skills/skills-codex/paper-figure - paper-illustration
skills/skills-codex/paper-illustration - paper-illustration-image2
skills/skills-codex/paper-illustration-image2 - paper-plan
skills/skills-codex/paper-plan - paper-poster
skills/skills-codex/paper-poster - paper-poster-html
skills/skills-codex/paper-poster-html - paper-slides
skills/skills-codex/paper-slides - paper-talk
skills/skills-codex/paper-talk - paper-write
skills/skills-codex/paper-write - paper-writing
skills/skills-codex/paper-writing - patent-novelty-check
skills/skills-codex/patent-novelty-check - patent-pipeline
skills/skills-codex/patent-pipeline - patent-review
skills/skills-codex/patent-review - pixel-art
skills/skills-codex/pixel-art - prior-art-search
skills/skills-codex/prior-art-search - proof-checker
skills/skills-codex/proof-checker - proof-orchestrator
skills/skills-codex/proof-orchestrator - proof-writer
skills/skills-codex/proof-writer - qzcli
skills/skills-codex/qzcli - rebuttal
skills/skills-codex/rebuttal - render-html
skills/skills-codex/render-html - research-implement-feature
skills/skills-codex/research-implement-feature - research-lit
skills/skills-codex/research-lit - research-pipeline
skills/skills-codex/research-pipeline - research-refine
skills/skills-codex/research-refine - research-refine-pipeline
skills/skills-codex/research-refine-pipeline - research-review
skills/skills-codex/research-review - research-wiki
skills/skills-codex/research-wiki - resubmit-pipeline
skills/skills-codex/resubmit-pipeline - result-to-claim
skills/skills-codex/result-to-claim - run-experiment
skills/skills-codex/run-experiment - semantic-scholar
skills/skills-codex/semantic-scholar - serverless-modal
skills/skills-codex/serverless-modal - slides-polish
skills/skills-codex/slides-polish - specification-writing
skills/skills-codex/specification-writing - system-profile
skills/skills-codex/system-profile - training-check
skills/skills-codex/training-check - vast-gpu
skills/skills-codex/vast-gpu - web-debug-search
skills/skills-codex/web-debug-search - wiki-enrich
skills/skills-codex/wiki-enrich - writing-systems-papers
skills/skills-codex/writing-systems-papers - slides-polish
skills/slides-polish - specification-writing
skills/specification-writing - system-profile
skills/system-profile - training-check
skills/training-check - vast-gpu
skills/vast-gpu - web-debug-search
skills/web-debug-search - wiki-enrich
skills/wiki-enrich - writing-systems-papers
skills/writing-systems-papers
How it works
ablation-planner
When your agent uses it
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,188 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- When to Use
- Workflow
- Rules
Files
../../.claude-plugin/marketplace.jsonasset1,151 bytes../../.claude-plugin/plugin.jsonasset703 bytesSKILL.mdcore5,137 bytes
Read SKILL.md
# Ablation Planner
Systematically design ablation studies that answer the questions reviewers will ask. Codex leads the design (reviewer perspective), CC reviews feasibility and implements.
## Context: $ARGUMENTS
## When to Use
- Main results pass `/result-to-claim` with claim_supported = yes or partial
- User explicitly requests ablation planning
- `/auto-review-loop` reviewer identifies missing ablations
## Workflow
alphaxiv
When your agent uses it
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
2,503 tokensWhen the skill is activated
Reference documents
6,960 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Workflow
- Key Rules
- Integration with Other Skills
Scripts executed separately
../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/skill_picker.py
Files
SKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytesSKILL.mdcore9,161 bytes../shared-references/integration-contract.mddoc26,858 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# AlphaXiv Paper Lookup
Lookup paper: $ARGUMENTS
> Quick single-paper reader with tiered source fallback (overview → full markdown → LaTeX source). Powered by [AlphaXiv](https://www.alphaxiv.org).
## Role & Positioning
This skill is the **quick single-paper reader** that returns LLM-optimized summaries:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Batch search, PDF download, metadata |
| `/deepxiv` | DeepXiv SDK | Progressive section-level reading |analyze-results
When your agent uses it
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
376 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Output Format
Files
SKILL.mdcore1,660 bytes
Read SKILL.md
# Analyze Experiment Results
Analyze: $ARGUMENTS
## Workflow
### Step 1: Locate Results
Find all relevant JSON/CSV result files:
- Check `figures/`, `results/`, or project-specific output directories
- Parse JSON results into structured data
### Step 2: Build Comparison Table
Organize results by:
- **Independent variables**: model type, hyperparameters, data configarxiv
When your agent uses it
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
2,710 tokensWhen the skill is activated
Reference documents
8,788 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Workflow
- Key Rules
Scripts executed separately
../../tools/arxiv_fetch.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/skill_picker.py
Files
SKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytesSKILL.mdcore9,289 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/wiki-helper-resolution.mddoc6,503 bytes../../tools/arxiv_fetch.pyruns11,762 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# arXiv Paper Search & Download
Search topic or arXiv paper ID: $ARGUMENTS
## Constants
- **PAPER_DIR** - Local directory to save downloaded PDFs. Default: `papers/` in the current project directory.
- **MAX_RESULTS = 10** - Default number of search results.
- **ARXIV_FETCHER** — canonical name `arxiv_fetch.py`, resolved per
[`shared-references/integration-contract.md`](../shared-references/integration-contract.md) §2
(Policy D1 — primary + fallback cascade). If unresolved (canonical
chain exhausted), fall back to the inline Python alternative
documented in Step 2.
auto-paper-improvement-loop
When your agent uses it
Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
What it loads into context
Frontmatter
246 tokensAlways available to the agent
SKILL.md
10,497 tokensWhen the skill is activated
Reference documents
10,566 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Constants
- Optional: Style reference (`— style-ref: <source>`, opt-in)
- Optional: Edit Whitelist (`— edit-whitelist <path>`, opt-in)
- Inputs
- State Persistence (Compact Recovery)
- Reviewer Independence Protocol
- Workflow
- Output
- Key Rules
- Typical Score Progression
- Review Tracing
Scripts executed separately
../../tools/extract_paper_style.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/skill_picker.py
Files
SKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytesSKILL.mdcore42,949 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/writing-principles.mddoc17,539 bytes../../tools/extract_paper_style.pyruns22,693 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Auto Paper Improvement Loop: Review → Fix → Recompile
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
auto-review-loop
When your agent uses it
Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.
What it loads into context
Frontmatter
229 tokensAlways available to the agent
SKILL.md
18,193 tokensWhen the skill is activated
Reference documents
21,566 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- Reviewer Calling Convention
- State Persistence (Compact Recovery)
- Output Protocols
- Workflow
- Key Rules
- Prompt Template for Round 2+
- Review Tracing
- Stop-Gate State-Transition Tests
Scripts executed separately
../../tools/review_gate.py
Files
SKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytesSKILL.mdcore75,537 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-routing.mddoc52,492 bytes../../tools/review_gate.pyruns20,528 bytes
Read SKILL.md
# Auto Review Loop: Autonomous Research Improvement
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It
> already loops internally (review → fix → re-review) and the reviewer carries
> round-to-round memory in one `threadId` (`codex-reply`). An external timer
> re-enters from the top each tick — fresh `threadId`, reviewer memory reset —
> firing the verdict on wall-clock time instead of on artifact change: zero new
> signal, full token cost. If you want to schedule something, schedule the
> *external wait that precedes it* (experiments done → then run this once). See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
Autonomously iterate: review → implement fixes → re-review, until an independent reviewer gives a policy-approved positive assessment or MAX_ROUNDS is reached.
## Context: $ARGUMENTSauto-review-loop-llm
When your agent uses it
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
2,542 tokensWhen the skill is activated
Reference documents
6,889 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- LLM Configuration
- API Call Method
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Prompt Template for Round 2+
- Output Protocols
Files
SKILL.mdcore9,243 bytesSKILL.mdcore9,243 bytesSKILL.mdcore9,243 bytesSKILL.mdcore9,243 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes
Read SKILL.md
# Auto Review Loop (Generic LLM): Autonomous Research Improvement
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** Like
> `/auto-review-loop`, it already loops internally (review → fix → re-review),
> feeding each round's prior-round summary into the next review prompt (the
> backend is a stateless per-round API/MCP call, not a shared thread). An
> external timer re-enters from the top each tick, dropping that accumulated
> context and firing the verdict on wall-clock time instead of on artifact
> change — zero new signal, full token cost. Schedule the *external wait that
> precedes it*, not the verdict. See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
auto-review-loop-minimax
When your agent uses it
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
3,247 tokensWhen the skill is activated
Reference documents
6,889 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- API Configuration
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Prompt Template for Round 2+
- Output Protocols
Files
SKILL.mdcore13,037 bytesSKILL.mdcore13,037 bytesSKILL.mdcore13,037 bytesSKILL.mdcore13,037 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes
Read SKILL.md
# Auto Review Loop (MiniMax Version): Autonomous Research Improvement
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** Like
> `/auto-review-loop`, it already loops internally (review → fix → re-review),
> feeding each round's prior-round summary into the next review prompt (the
> backend is a stateless per-round API call, not a shared thread). An external
> timer re-enters from the top each tick, dropping that accumulated context and
> firing the verdict on wall-clock time instead of on artifact change — zero
> new signal, full token cost. Schedule the *external wait that precedes it*,
> not the verdict. See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
citation-audit
When your agent uses it
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
What it loads into context
Frontmatter
238 tokensAlways available to the agent
SKILL.md
7,858 tokensWhen the skill is activated
Reference documents
6,768 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Catches
- Constants
- Workflow
- Uncited Entry Detection (opt-in)
- Key Rules
- Comparison with Other Audit Skills
- Known Limitations
- Review Tracing
- Output Contract
- Optional: Soft-Only Mode (— soft-only)
- Submission Artifact Emission
- See Also
Files
SKILL.mdcore32,168 bytesSKILL.mdcore32,168 bytesSKILL.mdcore32,168 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Citation Audit
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It iscitation-crosscheck
When your agent uses it
Double-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web while blind to the .bib, and a third extractor emits a mechanical field-by-field delta to catch dropped/re-ordered authors, wrong years, wrong venues, and bad DOIs/arXiv ids. The main agent (never a shard) assigns the MATCH/MINOR/MISMATCH verdict per reference, and exports a side-by-side spreadsheet. Use when user says "citation crosscheck", "double-blind citation check", "verify bib against scholar", "bib field audit", "引用交叉核对", or before submission when bibliography FIELD accuracy (not just existence) must be certified.
What it loads into context
Frontmatter
214 tokensAlways available to the agent
SKILL.md
10,010 tokensWhen the skill is activated
Reference documents
20,966 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this exists (and how it differs from `citation-audit`)
- Constants
- Workflow
- Key rules
Scripts executed separately
scripts/cx_verify.py
Files
SKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesSKILL.mdcore36,593 bytesscripts/cx_verify.pyruns84,510 bytes../shared-references/acceptance-gate.mddoc16,967 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/fan-out-pattern.mddoc21,698 bytes../shared-references/integration-contract.mddoc26,858 bytes
Read SKILL.md
# Citation Cross-Check (double-blind bib-vs-web field audit)
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is
> verdict-bearing — it emits a per-reference verdict that gates `.bib` edits (an evidence
> instrument, not a cross-model acquittal; see the acceptance-gate note in Step 2).
> Re-running it on a timer adds no signal (the verdict changes only when the
> *bibliography* changes).
> Schedule the external wait that precedes it: bibliography finalized → run once. See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
## Why this exists (and how it differs from `citation-audit`)
`citation-audit` is a single cross-model reviewer that judges three things holistically:
existence, metadata, and **context-fit** (is the cited paper used for a claim itclaims-drafting
When your agent uses it
Draft patent claims for an invention. Use when user says "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", or wants to create patent claims. The core skill of the patent pipeline.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
2,796 tokensWhen the skill is activated
Reference documents
9,224 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore11,296 bytes../shared-references/patent-format-cn.mddoc9,352 bytes../shared-references/patent-format-ep.mddoc6,542 bytes../shared-references/patent-format-us.mddoc6,151 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Claims Drafting: The Core Patent Skill
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Draft patent claims based on: **$ARGUMENTS**comm-lit-review
When your agent uses it
Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
2,112 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Constants
- Source Selection
- Retrieval Order
- External Search Policy
- Venue Priority
- Workflow
- Synthesis Rules
- Output
- Key Rules
Files
SKILL.mdcore8,683 bytesSKILL.mdcore8,683 bytesSKILL.mdcore8,683 bytesSKILL.mdcore8,683 bytes
Read SKILL.md
# Comm Lit Review Claude Single
Research topic: $ARGUMENTS
## Purpose
Use this skill for communications-domain literature review when the topic is about:
- wireless communications
- cellular systems, `4G/5G/6G`, `NR`, `NTN`
- satellite, `LEO`, `GEO`, integrated space-air-ground systems
- Wi-Fi, WLAN, mesh, ad hoc, sidelink, V2X
- routing, scheduling, resource allocation, beamforming
- rate adaptation, link adaptation, `ACM`, `HARQ`, `CSI` feedbackdeepxiv
When your agent uses it
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,500 tokensWhen the skill is activated
Reference documents
8,788 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../tools/deepxiv_fetch.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/skill_picker.py
Files
SKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytesSKILL.mdcore8,739 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/wiki-helper-resolution.mddoc6,503 bytes../../tools/deepxiv_fetch.pyruns6,222 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# DeepXiv Paper Search & Progressive Reading
Search topic or paper ID: $ARGUMENTS
## Role & Positioning
DeepXiv is the **progressive-reading** literature source:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Batch search, PDF download, metadata |
| **`/deepxiv`** | **DeepXiv SDK** | **Progressive section-level reading** |
| `/semantic-scholar` | S2 API | Published venue metadata, citation counts |
| `/alphaxiv` | www.alphaxiv.org | Instant LLM-optimized summary of one paper, with LaTeX source fallback |dse-loop
When your agent uses it
Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says "DSE", "design space exploration", "sweep parameters", "optimize", "find best config", or wants iterative parameter tuning.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
3,581 tokensWhen the skill is activated
Reference documents
4,592 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Safety Rules — READ FIRST
- Constants (override via $ARGUMENTS)
- Typical Use Cases
- Workflow
- State Recovery
- Key Rules
- Example Invocations
Files
SKILL.mdcore14,175 bytesSKILL.mdcore14,175 bytesSKILL.mdcore14,175 bytesSKILL.mdcore14,175 bytesSKILL.mdcore14,175 bytes../shared-references/external-cadence.mddoc19,084 bytes
Read SKILL.md
# DSE Loop: Autonomous Design Space Exploration
> 🔁 **Do not wrap this skill in `/loop` / `CronCreate`.** It already loops
> internally until its objective is met or it times out. Unlike the
> verdict-bearing review/audit skills, its stop gate is an **objective
> machine-checkable metric** (Type-A), so its self-termination is safe
> same-model — the reason not to wrap it is **scheduler duplication**, not the
> verdict fence. See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
Autonomously explore a design space: run → analyze → pick next parameters → repeat, until the objective is met or timeout is reached. Designed for computer architecture and EDA problems.
## Context: $ARGUMENTS
embodiment-description
When your agent uses it
Write detailed embodiment descriptions for patent specifications. Use when user says "撰写实施例", "write embodiment", "实施例描述", "detailed description", or wants to describe how to practice an invention.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,500 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Workflow
- Key Rules
Files
SKILL.mdcore6,732 bytesSKILL.mdcore6,732 bytesSKILL.mdcore6,732 bytes
Read SKILL.md
# Embodiment Description
Write detailed embodiments for: **$ARGUMENTS**
Embodiments describe HOW to make and use the invention -- they are the patent equivalent of experiment sections, but describe the invention rather than evaluating it empirically.
## Constants
- `MIN_EMBODIMENTS = 1` — At least one complete embodiment required
- `MAX_EMBODIMENTS = 3` — Practical limit; more embodiments strengthen enablement
- `EMBODIMENT_STYLE = detailed` — `detailed` (full working example) or `outline` (sketch)
- `REFERENCE_NUMERAL_PREFIX = 100` — Starting reference numeral for first figure's components
## Inputsexa-search
When your agent uses it
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,387 tokensWhen the skill is activated
Reference documents
8,788 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../tools/exa_search.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/skill_picker.py
Files
SKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytesSKILL.mdcore8,672 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/wiki-helper-resolution.mddoc6,503 bytes../../tools/exa_search.pyruns14,437 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Exa AI-Powered Web Search
Search query: $ARGUMENTS
## Role & Positioning
Exa is the **broad web search** source with built-in content extraction:
| Skill | Best for |
|------|----------|
| `/arxiv` | Direct preprint search and PDF download |
| `/semantic-scholar` | Published venue papers (IEEE, ACM, Springer), citation counts |
| `/deepxiv` | Layered reading: search, brief, section map, section reads |
| `/exa-search` | Broad web search: blogs, docs, news, companies, research papers — with content extraction |experiment-audit
When your agent uses it
Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
What it loads into context
Frontmatter
233 tokensAlways available to the agent
SKILL.md
3,345 tokensWhen the skill is activated
Reference documents
6,768 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- Core Principle
- Constants
- Reviewer Calling Convention
- Workflow
- Integration with Other Skills
- Key Rules
- Acknowledgements
- Review Tracing
Files
SKILL.mdcore13,750 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Experiment Audit: Cross-Model Integrity Verification
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It isexperiment-bridge
When your agent uses it
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
What it loads into context
Frontmatter
222 tokensAlways available to the agent
SKILL.md
4,747 tokensWhen the skill is activated
Reference documents
4,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Inputs
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
SKILL.mdcore19,701 bytesSKILL.mdcore19,701 bytesSKILL.mdcore19,701 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Workflow 1.5: Experiment Bridge
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Implement and deploy experiments from plan: **$ARGUMENTS**experiment-plan
When your agent uses it
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
2,209 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
SKILL.mdcore9,728 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes
Read SKILL.md
# Experiment Plan: Claim-Driven, Paper-Oriented Validation
Refine and concretize: **$ARGUMENTS**
## Overview
Use this skill after the method is stable enough that the next question becomes: **what exact experiments should we run, in what order, to defend the paper?** If the user wants the full chain in one request, prefer `/research-refine-pipeline`.
The goal is not to generate a giant benchmark wishlist. The goal is to turn a proposal into a **claim -> evidence -> run order** roadmap that supports four things:
1. the method actually solves the anchored problem
2. the dominant contribution is real and focused
3. the method is elegant enough that extra complexity is unnecessary
4. any frontier-model-era component is genuinely useful, not decorativeexperiment-queue
When your agent uses it
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
5,370 tokensWhen the skill is activated
Reference documents
7,238 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Why This Exists
- Core Concepts
- Workflow
- Grid Spec Syntax
- Wave Chaining
- OOM Handling
- Stale Screen Detection
- Resume-on-restart
- Output: Summary Report
- Comparison with `/run-experiment`
- Key Rules
- Known Failure Modes
- Example Session
- See Also
- Rationale / Source
Scripts executed separately
scripts/build_manifest.pyscripts/queue_manager.py../../tools/experiment_queue/build_manifest.py../../tools/experiment_queue/queue_manager.py
Files
SKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesSKILL.mdcore20,108 bytesscripts/build_manifest.pyruns4,562 bytesscripts/queue_manager.pyruns15,116 bytes../shared-references/compute-env-contract.mddoc10,567 bytes../shared-references/external-cadence.mddoc19,084 bytes../../tools/experiment_queue/build_manifest.pyruns1,542 bytes../../tools/experiment_queue/queue_manager.pyruns1,574 bytes
Read SKILL.md
# Experiment Queue
> ⏱ **External cadence: visibility only.** This skill already runs its own
> detached server-side scheduler (60s poll + `depends_on` + wave transitions).
> Use its status output for overnight visibility (N done / N running / N
> pending); do **not** wrap it in a second `/loop` / `CronCreate` poll — that
> duplicates the scheduler on an uncoordinated clock and races the
> wave-transition logic it was built to prevent. See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md)
> ("don't duplicate an existing scheduler").
Orchestrate large batches of ML experiments on SSH remote GPU servers with proper state tracking, OOM retry, stale cleanup, and wave transitions.
## When to Use This Skillfeishu-notify
When your agent uses it
Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,598 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Configuration
- Workflow
- Helper Function (for other skills)
- Event Catalog
- Key Rules
Files
SKILL.mdcore6,172 bytesSKILL.mdcore6,172 bytesSKILL.mdcore6,172 bytesSKILL.mdcore6,172 bytesSKILL.mdcore6,172 bytes
Read SKILL.md
# Feishu/Lark Notification
Send a notification: **$ARGUMENTS**
## Overview
This skill provides Feishu/Lark integration for ARIS. It is designed as an **internal utility** — other skills call it at key events (experiment done, review scored, checkpoint waiting). It can also be invoked manually.
**Zero-impact guarantee**: If no `feishu.json` config exists, this skill does nothing and returns silently. All existing workflows are completely unaffected.
## Configuration
The skill reads `~/.claude/feishu.json`. If this file does not exist, **all Feishu functionality is disabled** — skills behave exactly as before.
figure-description
When your agent uses it
Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with reference numerals.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,239 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Workflow
- Key Rules
Files
SKILL.mdcore5,000 bytes
Read SKILL.md
# Figure Description for Patents
Process patent figures and generate drawing descriptions based on: **$ARGUMENTS**
Unlike `/paper-figure` which generates data plots, this skill processes user-provided technical diagrams and assigns reference numerals.
## Constants
- `FIGURE_DIR = "patent/figures/"` — Output directory for figure descriptions
- `REFERENCE_NUMERAL_PREFIX = 100` — Starting numeral for first figure's components
- `NUMERAL_SERIES = 100` — Each figure uses a separate 100-series (Fig 1: 100-199, Fig 2: 200-299, etc.)
## Inputs
figure-spec
When your agent uses it
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
What it loads into context
Frontmatter
209 tokensAlways available to the agent
SKILL.md
3,266 tokensWhen the skill is activated
Reference documents
9,136 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Core Properties
- Tool Location
- Workflow
- Schema Quick Reference
- Design Patterns
- Anti-Patterns
- Output Contract
- Integration with Other Skills
- Review Tracing
Scripts executed separately
scripts/figure_renderer.py../../tools/figure_renderer.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/skill_picker.py
Files
SKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesSKILL.mdcore12,080 bytesscripts/figure_renderer.pyruns29,876 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../tools/figure_renderer.pyruns2,582 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# FigureSpec: Deterministic JSON → SVG Figure Generation
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate publication-quality **architecture diagrams**, **workflow pipelines**, **audit cascades**, and **system topology** figures as editable SVG vector graphics using a deterministic JSON → SVG renderer.firecrawl-search
When your agent uses it
Web search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search".
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
3,050 tokensWhen the skill is activated
Reference documents
13,685 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../tools/firecrawl_search.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/skill_picker.py
Files
SKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytesSKILL.mdcore11,000 bytes../shared-references/citation-discipline.mddoc20,131 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/wiki-helper-resolution.mddoc6,503 bytes../../tools/firecrawl_search.pyruns15,149 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Firecrawl Web Search and Scrape
Search query or URL: $ARGUMENTS
## Role & Positioning
Firecrawl is a **broad web search** source that returns the full page as markdown, plus a scraper for URLs you already have:
| Skill | Best for |
|------|----------|
| `/arxiv` | Direct preprint search and PDF download |
| `/semantic-scholar` | Published venue papers (IEEE, ACM, Springer), citation counts |
| `/openalex` | Open citation graph, affiliations, funding metadata |
| `/deepxiv` | Layered reading: search, brief, section map, section reads |formula-derivation
When your agent uses it
Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
2,064 tokensWhen the skill is activated
Reference documents
4,480 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Context: $ARGUMENTS
- Goal
- Inputs
- Workflow
- Required File Structure
- Output Modes
- Relationship to `proof-writer`
- Chat Response
- Key Rules
Files
SKILL.mdcore9,550 bytes../lean-formalize/SKILL.mddoc22,797 bytes
Read SKILL.md
# Formula Derivation: Research Theory Line Construction
Build an honest derivation package, not a fake polished theorem story.
## Constants
- DEFAULT_DERIVATION_DOC = `DERIVATION_PACKAGE.md` in project root
- STATUS = `COHERENT AS STATED | COHERENT AFTER REFRAMING / EXTRA ASSUMPTION | NOT YET COHERENT`
## Context: $ARGUMENTS
## Goal
Produce exactly one of:gemini-search
When your agent uses it
Search research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literature discovery beyond arXiv/Semantic Scholar indexes.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
2,473 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Environment & Setup
- Workflow
- Key Rules
Files
SKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytesSKILL.mdcore9,324 bytes
Read SKILL.md
# Gemini Literature Search
Search query: $ARGUMENTS
## Role & Positioning
This skill uses Gemini as a **broad literature discovery** source:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |
| `/semantic-scholar` | Semantic Scholar API | Published venue papers (IEEE, ACM, Springer) with citation counts |
| `/deepxiv` | DeepXiv CLI | Layered reading: search, brief, section map, section reads |
| `/exa-search` | Exa API | Broad web search: blogs, docs, news, companies, research papers |grant-proposal
When your agent uses it
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.
What it loads into context
Frontmatter
294 tokensAlways available to the agent
SKILL.md
8,893 tokensWhen the skill is activated
Reference documents
4,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Optional: Style reference (`— style-ref: <source>`, opt-in)
- Grant Type Specifications
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Parameter Pass-Through
- Composing with Other Skills
- Output Protocols
Scripts executed separately
../../tools/extract_paper_style.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/skill_picker.py
Files
SKILL.mdcore36,109 bytesSKILL.mdcore36,109 bytesSKILL.mdcore36,109 bytesSKILL.mdcore36,109 bytesSKILL.mdcore36,109 bytesSKILL.mdcore36,109 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../tools/extract_paper_style.pyruns22,693 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Grant Proposal: From Research Ideas to Fundable Application
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Draft a grant proposal based on: **$ARGUMENTS**idea-creator
When your agent uses it
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
What it loads into context
Frontmatter
225 tokensAlways available to the agent
SKILL.md
8,633 tokensWhen the skill is activated
Reference documents
34,188 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Reviewer Calling Convention
- Workflow
- Phase 7: Write Ideas to Research Wiki (if active)
- Output Protocols
- Key Rules
- Composing with Other Skills
- Review Tracing
Scripts executed separately
../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/skill_picker.py../../tools/threat_scan.py
Files
SKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytesSKILL.mdcore35,181 bytes../research-wiki/SKILL.mddoc20,553 bytes../shared-references/acceptance-gate.mddoc16,967 bytes../shared-references/citation-discipline.mddoc20,131 bytes../shared-references/fan-out-pattern.mddoc21,698 bytes../shared-references/injection-hygiene.mddoc7,468 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/output-composition.mddoc5,005 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes../../tools/threat_scan.pyruns12,166 bytes
Read SKILL.md
# Research Idea Creator
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate publishable research ideas for: $ARGUMENTSidea-discovery
When your agent uses it
Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
6,892 tokensWhen the skill is activated
Reference documents
10,223 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Checkpoint execution rule
- Per-stage evidence gate (`RESUMABLE = true`)
- Pipeline
- Output Protocols
- Render HTML view (auto, when `RENDER_HTML = true`)
- Key Rules
- Composing with Workflow 2
Files
SKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytesSKILL.mdcore28,404 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/output-composition.mddoc5,005 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Workflow 1: Idea Discovery Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Orchestrate a complete idea discovery workflow for: **$ARGUMENTS**idea-discovery-robot
When your agent uses it
Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
3,544 tokensWhen the skill is activated
Reference documents
4,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Execution Rule
- Phase 0: Frame the Robotics Problem
- Phase 1: Robotics Literature Survey
- Phase 2: Robotics-Specific Idea Generation and Filtering
- Phase 3: Feasibility and Pilot Design
- Phase 4: Deep Novelty Verification
- Phase 5: External Robotics Review
- Phase 6: Final Report
- Key Rules
- Composing with Later Work
- Output Protocols
Files
SKILL.mdcore15,971 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Robotics Idea Discovery Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Orchestrate a robotics-specific idea discovery workflow for: **$ARGUMENTS**integrity-forensics
When your agent uses it
Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher — then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Use when user says "integrity forensics", "forensic audit this paper", "投稿前自查诚信", "审这篇论文的诚信", or says "anti-autoresearch" when the upstream repo's own skills are not installed. Also invoked by /paper-writing (submission self-forensics, default ON), /peer-review (forensic appendix), /resubmit-pipeline.
What it loads into context
Frontmatter
203 tokensAlways available to the agent
SKILL.md
4,302 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Step 0 — Bootstrap the pin (idempotent)
- Step 1 — Delegate: run the upstream sweep, unchanged
- Step 2 — Typed gate + obligations (ARIS-side post-processing)
- Step 3 — Fix what it found (obligations, not a polish loop)
- Trust boundary (what is computed vs what is protocol)
- Pin-bump checklist (maintainers)
- Codex-native note (mirror)
- Review tracing
Scripts executed separately
../../tools/forensics_gate.py
Files
SKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytes../../tools/forensics_gate.pyruns32,705 bytes
Read SKILL.md
# Integrity Forensics — thin launcher for Anti-Autoresearch
Audit target: **$ARGUMENTS**
> **What this is.** ARIS generates papers; [Anti-Autoresearch](https://github.com/wanshuiyin/Anti-Autoresearch)
> is its outward-pointed dual — reviewer-side integrity forensics (46 patterns
> across 8 families, deterministic GRIM/GRIMMER/statcheck core, span-anchored
> claims, a rules-only reporter that summarizes rather than adjudicates). This skill is a
> **thin launcher**: it pins an upstream commit, validates the pin with the
> upstream eval gate, delegates execution unchanged, and post-processes the
> verdict into ARIS's policy vocabulary. It vendors nothing and forks nothing.
> 🔁 **Cadence fence** (`shared-references/external-cadence.md`): this skill is
> verdict-bearing decision support. Do not wrap it in `/loop` / `/schedule` —interview-cheatsheet
When your agent uses it
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.
What it loads into context
Frontmatter
270 tokensAlways available to the agent
SKILL.md
3,866 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- Style guide — STRICT (read `docs/tutorials/attention_tutorial.md` as canonical reference)
- Workflow
- Update the index
- Key invariants (the ARIS rules baked in)
- When NOT to use
- Reference invocations
- Reference style files
- Provenance
Files
SKILL.mdcore14,586 bytesSKILL.mdcore14,586 bytesSKILL.mdcore14,586 bytesSKILL.mdcore14,586 bytesSKILL.mdcore14,586 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# /interview-cheatsheet — long-form Chinese ML/LLM interview prep
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate one comprehensive Chinese cheat sheet per invocation: formulas + derivations + from-scratch code + 25 高频题. Output passes cross-model math/code review before rendering. **Detect-only by default: never auto-commits.**invention-structuring
When your agent uses it
Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
1,742 tokensWhen the skill is activated
Reference documents
4,128 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore7,907 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Invention Structuring
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Structure the invention into a formal disclosure based on: **$ARGUMENTS**jurisdiction-format
When your agent uses it
Compile patent application into jurisdiction-specific filing format. Use when user says "格式转换", "jurisdiction format", "国家格式", "compile patent", or wants formatted patent documents for CN/US/EP filing.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,689 tokensWhen the skill is activated
Reference documents
5,096 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore6,816 bytes../shared-references/patent-format-cn.mddoc9,352 bytes../shared-references/patent-format-ep.mddoc6,542 bytes../shared-references/patent-format-us.mddoc6,151 bytes
Read SKILL.md
# Jurisdiction Format: Patent Filing Compilation
Compile the patent application into filing-ready format based on: **$ARGUMENTS**
Analogous to `/paper-compile` but for patent document formatting instead of LaTeX.
## Constants
- `JURISDICTION = "auto"` — From pipeline or args: `CN`, `US`, `EP`, `ALL`
- `PATENT_TYPE = "invention"` — `invention` (发明专利) or `utility_model` (实用新型, CN only)
- `OUTPUT_FORMAT = "markdown"` — `markdown` (for review) or `docx` (for filing, requires python-docx)
- `OUTPUT_DIR = "patent/output/"` — Base output directory
## Inputskeenable-search
When your agent uses it
Keyless web search and page fetch via Keenable. Use when user says "keenable search", "web search without an API key", "fetch this page as markdown", or needs broad web results beyond academic databases (arXiv, Semantic Scholar) with no search API key set up.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,676 tokensWhen the skill is activated
Reference documents
6,960 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/keenable_search.py../../tools/skill_picker.py
Files
SKILL.mdcore6,230 bytesSKILL.mdcore6,230 bytesSKILL.mdcore6,230 bytesSKILL.mdcore6,230 bytesSKILL.mdcore6,230 bytesSKILL.mdcore6,230 bytesSKILL.mdcore6,230 bytes../shared-references/integration-contract.mddoc26,858 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/keenable_search.pyruns11,367 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Keenable Web Search
Search query: $ARGUMENTS
## Role & Positioning
Keenable is a **broad web search** source that works without an API key or extra Python packages:
| Skill | Best for |
|------|----------|
| `/arxiv` | Direct preprint search and PDF download |
| `/semantic-scholar` | Published venue papers (IEEE, ACM, Springer), citation counts |
| `/exa-search` | Broad web search with content extraction (highlights, summaries); needs `EXA_API_KEY` |
| `/keenable-search` | Broad web search with a page-text snippet per result, plus fetching a known URL as markdown; no key needed |kill-argument
When your agent uses it
Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.
What it loads into context
Frontmatter
220 tokensAlways available to the agent
SKILL.md
6,386 tokensWhen the skill is activated
Reference documents
11,949 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- How This Differs From Other Review Skills
- When To Use
- Constants
- Workflow
- Output Contract
- Key Rules
- When NOT to Use
- Review Tracing
- Notes
Files
SKILL.mdcore26,120 bytesSKILL.mdcore26,120 bytesSKILL.mdcore26,120 bytesSKILL.mdcore26,120 bytesSKILL.mdcore26,120 bytesSKILL.mdcore26,120 bytesSKILL.mdcore26,120 bytesSKILL.mdcore26,120 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/fan-out-pattern.mddoc21,698 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Kill Argument Exercise: Adversarial Attack-Defense Review
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It islean-formalize
When your agent uses it
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific proof obligation benefits from formal verification; use proof-writer for ordinary mathematical drafting.
What it loads into context
Frontmatter
237 tokensAlways available to the agent
SKILL.md
4,480 tokensWhen the skill is activated
Reference documents
26,095 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use Lean
- Core workflow
- Scope and entry
- 1. Fix meaning before implementation
- 2. Design the connections, then build useful pieces
- 3. Use computation with a proved interpretation
- 4. Review the mathematical obligations that remain uncertain
- 5. Verify the actual final target
- 6. Persist and hand off the evidence actually obtained
Files
SKILL.mdcore22,797 bytesSKILL.mdcore22,797 bytesSKILL.mdcore22,797 bytesSKILL.mdcore22,797 bytesSKILL.mdcore22,797 bytesreferences/adversarial-review.mddoc14,165 bytesreferences/lean-working-loop.mddoc10,625 bytesreferences/verification-and-handoff.mddoc6,332 bytes../shared-references/fan-out-pattern.mddoc21,698 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-routing.mddoc52,492 bytes
Read SKILL.md
# Lean Formalize
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Turn the user's mathematical statement into a checked Lean theorem with itsmermaid-diagram
When your agent uses it
Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
4,109 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Workflow: MUST EXECUTE ALL STEPS
- Architecture Diagram Best Practices
- CVPR/ICLR/NeurIPS Style Guide (for Academic Diagrams)
- Math Formulas in Diagrams (KaTeX)
- Code Quality Rules
- Output Structure
- Key Rules (MUST FOLLOW)
Files
SKILL.mdcore16,323 bytesSKILL.mdcore16,323 bytesSKILL.mdcore16,323 bytesSKILL.mdcore16,323 bytesSKILL.mdcore16,323 bytesSKILL.mdcore16,323 bytesSKILL.mdcore16,323 bytesSKILL.mdcore16,323 bytes
Read SKILL.md
# Mermaid Diagram Generator
Generate high-quality Mermaid diagram code based on user requirements, with file output and verification.
## Constants
- **OUTPUT_DIR = `figures/`** — Output directory for all generated files
- **MAX_ITERATIONS = 3** — Maximum refinement rounds for syntax errors
## Workflow: MUST EXECUTE ALL STEPS
### Step 0: Pre-flight Check
```bashmeta-apply
When your agent uses it
Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury and human approval at landing. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
What it loads into context
Frontmatter
227 tokensAlways available to the agent
SKILL.md
2,262 tokensWhen the skill is activated
Reference documents
23,066 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The acquittal is generated HERE, not relayed
- The non-negotiable rules (jury-at-landing, reject-default)
- Workflow
- Provenance is a receipt, not an acquittal of correctness
- Key Rules
- Review Tracing
Files
SKILL.mdcore8,983 bytesSKILL.mdcore8,983 bytesSKILL.mdcore8,983 bytes../meta-optimize/SKILL.mddoc24,917 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/review-scope-limits.mddoc4,174 bytes../shared-references/review-tracing.mddoc23,757 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc3,473 bytes
Read SKILL.md
# Meta-Apply: the privileged landing gate for self-modification patches
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
This skill exists to enforce a **privilege boundary**. Producers likemeta-optimize
When your agent uses it
Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
6,088 tokensWhen the skill is activated
Reference documents
12,074 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Privilege boundary — this skill is a READ-ONLY PRODUCER
- Context
- What This Skill Optimizes (Harness Components)
- Prerequisites
- Workflow
- Key Rules
- Event Schema Reference
- Triggering
- Acknowledgements
- Output Protocols
- Review Tracing
Scripts executed separately
../../tools/capture_filter.py../../tools/meta_opt/trigger_eval.py
Files
../meta-apply/SKILL.mddoc8,983 bytesSKILL.mdcore24,917 bytesSKILL.mdcore24,917 bytesSKILL.mdcore24,917 bytesSKILL.mdcore24,917 bytes../shared-references/acceptance-gate.mddoc16,967 bytes../shared-references/capture-antipatterns.mddoc4,516 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../templates/claude-hooks/corpus_write_guard.jsonasset837 bytes../../tools/capture_filter.pyruns6,080 bytes../../tools/meta_opt/trigger_eval.pyruns13,384 bytes../../tools/meta_opt/trigger_evals.sample.jsonasset1,570 bytes
Read SKILL.md
# Meta-Optimize: Outer-Loop Harness Optimization for ARIS
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Analyze accumulated usage logs and propose optimizations for: **$ARGUMENTS**monitor-experiment
When your agent uses it
Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,321 tokensWhen the skill is activated
Reference documents
4,592 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Rules
Files
SKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytesSKILL.mdcore5,050 bytes../shared-references/external-cadence.mddoc19,084 bytes
Read SKILL.md
# Monitor Experiment Results
> ⏱ **External cadence is appropriate here.** This skill waits on an external
> fact (job completion / progress), so it is a natural `/loop` / `CronCreate`
> surface: the wake reads status and self-judges only **machine-checkable**
> completion (exit code, file exists, epoch logged) — never quality. This is
> the additive external-wait shape in
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
> If a scheduled wait here ends in a verdict step (e.g. then audit results),
> run that verdict **once** after the wait clears — not re-entered per tick.
Monitor: $ARGUMENTS
## Workflownovelty-check
When your agent uses it
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
2,033 tokensWhen the skill is activated
Reference documents
14,033 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Instructions
- Review Tracing
Files
SKILL.mdcore8,331 bytes../shared-references/citation-discipline.mddoc20,131 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Novelty Check Skill
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Check whether a proposed method/idea has already been done in the literature: **$ARGUMENTS**openalex
When your agent uses it
Search academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
2,676 tokensWhen the skill is activated
Reference documents
6,960 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
- OpenAlex vs Other Sources
Scripts executed separately
../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/openalex_fetch.py../../tools/skill_picker.py
Files
SKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytesSKILL.mdcore9,988 bytes../shared-references/integration-contract.mddoc26,858 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/openalex_fetch.pyruns12,106 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# OpenAlex Academic Search
Search query: $ARGUMENTS
## Role & Positioning
This skill uses OpenAlex as a **comprehensive open academic graph** source:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |
| `/semantic-scholar` | Semantic Scholar API | Published venue papers (IEEE, ACM, Springer) with citation counts |
| `/openalex` | OpenAlex API | **Open citation graph, institutional affiliations, funding data, comprehensive metadata** |
| `/deepxiv` | DeepXiv CLI | Layered reading: search, brief, section map, section reads |overleaf-sync
When your agent uses it
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to bridge their ARIS paper directory with an Overleaf project.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
2,842 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Constants
- Architecture
- Sub-commands
- Conflict Resolution
- Token Security — Defense in Depth
- Mutual-Exclusion Rule
- Output Contract
- See Also
Scripts executed separately
../../tools/overleaf_audit.sh../../tools/overleaf_setup.sh
Files
SKILL.mdcore11,122 bytesSKILL.mdcore11,122 bytesSKILL.mdcore11,122 bytesSKILL.mdcore11,122 bytesSKILL.mdcore11,122 bytesSKILL.mdcore11,122 bytesSKILL.mdcore11,122 bytesSKILL.mdcore11,122 bytes../../tools/overleaf_audit.shruns3,516 bytes../../tools/overleaf_setup.shruns6,412 bytes
Read SKILL.md
# Overleaf Sync
Bridge a local paper directory with an Overleaf project so that:
- **You** can keep editing in the Overleaf web UI (or share editing access with collaborators)
- **ARIS** can read your changes, run audits (`/paper-claim-audit`, `/citation-audit`, `/auto-paper-improvement-loop`), and push fixes back
This uses the official **Overleaf Git bridge** (Premium feature). The agent **never sees your authentication token** — you do the one-time auth manually so the token lives in macOS Keychain, not in chat history or `.git/config`.
## When to Use This Skill
- You want to use Overleaf as the editing surface (better collaboration, shared with team) but still run ARIS pipelines locally
- You want to take an existing local ARIS paper and push it to Overleaf for a co-author to edit
- A collaborator made changes in Overleaf and you want to pull + diff them before continuing local workpaper-claim-audit
When your agent uses it
Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
3,854 tokensWhen the skill is activated
Reference documents
6,768 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- How This Differs From Other Audit Skills
- Core Principle
- Workflow
- When to Run
- Integration with Other Skills
- Render HTML view (auto, when `RENDER_HTML = true`, default)
- Key Rules
- Review Tracing
- Submission Artifact Emission
Files
SKILL.mdcore15,356 bytesSKILL.mdcore15,356 bytesSKILL.mdcore15,356 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Paper Claim Audit: Zero-Context Evidence Verification
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It ispaper-compile
When your agent uses it
Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
2,661 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Workflow
- Key Rules
- Common Venue Requirements
Files
SKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytesSKILL.mdcore10,070 bytes
Read SKILL.md
# Paper Compile: LaTeX to Submission-Ready PDF
Compile the LaTeX paper and fix any issues: **$ARGUMENTS**
## Constants
- **COMPILER = `latexmk`** — LaTeX build tool. Handles multi-pass compilation automatically.
- **ENGINE = `pdflatex`** — LaTeX engine. Options: `pdflatex` (default), `xelatex` (for CJK/custom fonts), `lualatex`.
- **MAX_COMPILE_ATTEMPTS = 3** — Maximum attempts to fix errors and recompile.
- **PAPER_DIR = `paper/`** — Directory containing LaTeX source files.
- **MAX_PAGES** — Page limit. ML conferences: main body to Conclusion end (excluding references & appendix). ICLR=9, NeurIPS=9, ICML=8. **IEEE venues: references ARE included in page count.** IEEE journal ≈ 12-14 pages, IEEE conference ≈ 5-8 pages (all inclusive).
## Workflow
paper-figure
When your agent uses it
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
3,848 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope: What This Skill Can and Cannot Do
- Constants
- Inputs
- Workflow
- Output
- Key Rules
- Figure Type Reference
- Acknowledgements
Files
SKILL.mdcore14,778 bytesSKILL.mdcore14,778 bytesSKILL.mdcore14,778 bytesSKILL.mdcore14,778 bytesSKILL.mdcore14,778 bytesSKILL.mdcore14,778 bytesSKILL.mdcore14,778 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Paper Figure: Publication-Quality Plots from Experiment Data
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate all figures and tables for a paper based on: **$ARGUMENTS**paper-illustration
When your agent uses it
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
7,832 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Design Philosophy
- Constants
- Optional: Style reference (`— style-ref: <source>`, opt-in)
- CVPR/ICLR/NeurIPS Top-Tier Conference Style Guide
- Scope
- Workflow: MUST EXECUTE ALL STEPS
- Key Rules (MUST FOLLOW - STRICT)
- Output Structure
- Model Summary
Scripts executed separately
../../tools/extract_paper_style.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/skill_picker.py
Files
SKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytesSKILL.mdcore33,241 bytes../../tools/extract_paper_style.pyruns22,693 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Paper Illustration: Multi-Stage Claude-Supervised Figure Generation
Generate publication-quality illustrations using a **multi-stage workflow** with **Claude as the STRICT supervisor/reviewer**.
## Core Design Philosophy
```
┌──────────────────────────────────────────────────────────────────────────┐
│ MULTI-STAGE ITERATIVE WORKFLOW │
├──────────────────────────────────────────────────────────────────────────┤
│ │
│ User Request │
│ │ │
│ ▼ │paper-illustration-image2
When your agent uses it
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to `paper-illustration`, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
What it loads into context
Frontmatter
239 tokensAlways available to the agent
SKILL.md
4,301 tokensWhen the skill is activated
Reference documents
9,136 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Design Philosophy
- Constants
- CVPR/ICLR/NeurIPS Top-Tier Conference Style Guide
- Scope
- Workflow: MUST EXECUTE ALL STEPS
- Step 1: Claude Plans the Figure
- Step 2: Layout Optimization
- Step 3: Style Verification
- Step 4: Generate Through the Bridge
- Step 5: Review the Output
- Step 6: Refine if Needed
- Step 7: Finalize And Verify
- Key Rules
- Repair Path
- Output Structure
- Model Summary
Scripts executed separately
scripts/paper_illustration_image2.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/paper_illustration_image2.py../../tools/skill_picker.py
Files
SKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesSKILL.mdcore19,831 bytesscripts/paper_illustration_image2.pyruns8,745 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/paper_illustration_image2.pyruns2,205 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Paper Illustration Image2
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate publication-quality paper figures using **Claude as the planner/reviewer**paper-plan
When your agent uses it
Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.
What it loads into context
Frontmatter
211 tokensAlways available to the agent
SKILL.md
5,512 tokensWhen the skill is activated
Reference documents
10,203 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Orchestra-Guided Writing Overlay
- Optional: Style reference (`— style-ref: <source>`, opt-in)
- Workflow
- Key Rules
- Acknowledgements
- Output Protocols
Scripts executed separately
../../tools/extract_paper_style.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/skill_picker.py
Files
SKILL.mdcore22,041 bytesSKILL.mdcore22,041 bytesSKILL.mdcore22,041 bytesSKILL.mdcore22,041 bytesSKILL.mdcore22,041 bytesSKILL.mdcore22,041 bytesSKILL.mdcore22,041 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc3,473 bytes../shared-references/venue-checklists.mddoc5,582 bytes../shared-references/writing-principles.mddoc17,539 bytes../../tools/extract_paper_style.pyruns22,693 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Paper Plan: From Review Conclusions to Paper Outline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
paper-poster
When your agent uses it
DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
192 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore828 bytesSKILL.mdcore828 bytes
Read SKILL.md
# Paper Poster (DEPRECATED → /paper-poster-html)
This skill is retired. The LaTeX/tcbposter pipeline it described produced posters with
unbounded color palettes, no real paper figures, and no print-canvas verification, and
has been replaced by the measurement-gated HTML/CSS pipeline.
**Immediately proceed with `/paper-poster-html`**, passing through all of the user's
arguments unchanged. Do not attempt the legacy LaTeX flow.
The full legacy implementation remains available in git history
(`git log -- skills/paper-poster/SKILL.md`) if a venue ever mandates LaTeX poster
source — none is known to.paper-poster-html
When your agent uses it
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster. Supersedes the retired LaTeX /paper-poster.
What it loads into context
Frontmatter
274 tokensAlways available to the agent
SKILL.md
4,930 tokensWhen the skill is activated
Reference documents
21,434 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this skill exists (the failure it prevents)
- Mental model
- Constants
- Workflow
- State persistence
- Key rules
- Review tracing
- Output contract
- When NOT to use
Scripts executed separately
scripts/_posterly/__init__.pyscripts/_posterly/canvas.pyscripts/_posterly/measure.pyscripts/_posterly/polish.pyscripts/_posterly/preflight.pyscripts/_posterly/render.pyscripts/_posterly/textutil.pyscripts/_posterly/verify_final.pyscripts/asset_check.pyscripts/extract_pdf_figures.pyscripts/poster_check.pyscripts/preprocess_figures.pyscripts/render_preview.pyscripts/run_gates.pyscripts/style_check.py
Files
DESIGN_FINAL.mddoc9,948 bytesIMPLEMENTATION_CONVENTIONS.mddoc8,942 bytesLICENSES/posterly-MIT.txtdoc1,069 bytesNOTICE.mddoc3,288 bytesSKILL.mdcore19,486 bytesSKILL.mdcore19,486 bytesSKILL.mdcore19,486 bytesSKILL.mdcore19,486 bytesSKILL.mdcore19,486 bytesSKILL.mdcore19,486 bytesSKILL.mdcore19,486 bytesSKILL.mdcore19,486 bytesscripts/_posterly/__init__.pyruns0 bytesscripts/_posterly/canvas.pyruns7,377 bytesscripts/_posterly/measure.pyruns24,692 bytesscripts/_posterly/polish.pyruns21,014 bytesscripts/_posterly/preflight.pyruns21,616 bytesscripts/_posterly/render.pyruns8,239 bytesscripts/_posterly/textutil.pyruns616 bytesscripts/_posterly/verify_final.pyruns5,683 bytesscripts/asset_check.pyruns36,805 bytesscripts/extract_pdf_figures.pyruns26,003 bytesscripts/poster_check.pyruns10,123 bytesscripts/preprocess_figures.pyruns9,306 bytesscripts/render_preview.pyruns7,670 bytesscripts/run_gates.pyruns20,482 bytesscripts/style_check.pyruns53,183 bytestemplates/COMPONENTS.mddoc31,274 bytestemplates/README.mddoc10,442 bytestemplates/landscape_4col.htmlasset41,841 bytestemplates/landscape_hero.htmlasset44,680 bytestemplates/portrait_2col.htmlasset40,424 bytestemplates/tokens/acl.jsonasset431 bytestemplates/tokens/cvpr.jsonasset432 bytestemplates/tokens/generic.jsonasset435 bytestemplates/tokens/iclr.jsonasset432 bytestemplates/tokens/icml.jsonasset432 bytestemplates/tokens/neurips.jsonasset435 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/taste-calibration.mddoc4,515 bytes
Read SKILL.md
# Paper Poster (HTML): measurement-gated poster generation
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
One HTML file styled for an exact print canvas (`@page { size: W H }`), rendered to PDFpaper-slides
When your agent uses it
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
What it loads into context
Frontmatter
236 tokensAlways available to the agent
SKILL.md
6,714 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Constants
- Optional: Style reference (`— style-ref: <source>`, opt-in)
- Talk Type → Slide Count
- Venue Color Schemes
- State Persistence (Compact Recovery)
- Workflow
- Recommended Follow-up: `/slides-polish`
- Key Rules
- Parameter Pass-Through
Scripts executed separately
../../tools/extract_paper_style.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/skill_picker.py
Files
SKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytesSKILL.mdcore24,121 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../tools/extract_paper_style.pyruns22,693 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Paper Slides: From Paper to Conference Talk
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate conference presentation slides from: **$ARGUMENTS**paper-talk
When your agent uses it
End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline", "end-to-end slides", "做演讲", "conference talk full workflow". Use when the user wants the complete talk artifact, not just a slide deck.
What it loads into context
Frontmatter
230 tokensAlways available to the agent
SKILL.md
5,422 tokensWhen the skill is activated
Reference documents
9,126 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Assurance Ladder
- Hard Invariants
- Constants
- Inputs
- Output Layout
- Workflow
- Effort Levels
- Parameter Pass-Through
- When NOT to Use
- Prior Skill Relationship
- Empirical Origin
Files
SKILL.mdcore21,676 bytesSKILL.mdcore21,676 bytesSKILL.mdcore21,676 bytesSKILL.mdcore21,676 bytesSKILL.mdcore21,676 bytesSKILL.mdcore21,676 bytes../shared-references/assurance-contract.mddoc13,572 bytes../shared-references/effort-contract.mddoc8,352 bytes../shared-references/experiment-integrity.mddoc2,355 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc3,473 bytes
Read SKILL.md
# Paper Talk: End-to-End Conference Talk Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Workflow: from a completed paper to a conference-ready talk artifact —paper-write
When your agent uses it
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
What it loads into context
Frontmatter
226 tokensAlways available to the agent
SKILL.md
9,698 tokensWhen the skill is activated
Reference documents
12,803 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Orchestra-Guided Writing Overlay
- Optional: Style reference (`— style-ref: <source>`, opt-in)
- Templates
- Workflow
- Key Rules
- Writing Quality Reference
- Acknowledgements
Scripts executed separately
../../tools/extract_paper_style.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/skill_picker.py
Files
SKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytesSKILL.mdcore39,957 bytestemplates/IEEEtran.bstasset57,748 bytestemplates/IEEEtran.clsasset281,957 bytestemplates/iclr2026.texasset1,924 bytestemplates/icml2025.texasset2,003 bytestemplates/ieee_conference.texasset2,124 bytestemplates/ieee_journal.texasset2,557 bytestemplates/math_commands.texasset1,279 bytestemplates/neurips2025.texasset1,829 bytes../shared-references/citation-discipline.mddoc20,131 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc3,473 bytes../shared-references/venue-checklists.mddoc5,582 bytes../shared-references/writing-principles.mddoc17,539 bytes../../tools/extract_paper_style.pyruns22,693 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Paper Write: Section-by-Section LaTeX Generation
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
paper-writing
When your agent uses it
Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.
What it loads into context
Frontmatter
234 tokensAlways available to the agent
SKILL.md
13,308 tokensWhen the skill is activated
Reference documents
20,329 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Inputs
- Optional: Style reference (`— style-ref: <source>`, opt-in)
- Pipeline
- Output Protocols
- Key Rules
- Composing with Other Workflows
- Typical Timeline
Scripts executed separately
../../tools/extract_paper_style.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/paper_illustration_image2.py../../tools/skill_picker.py../../tools/verify_paper_audits.sh
Files
../integrity-forensics/SKILL.mddoc17,170 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytesSKILL.mdcore52,667 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc3,473 bytes../shared-references/writing-principles.mddoc17,539 bytes../../tools/extract_paper_style.pyruns22,693 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/paper_illustration_image2.pyruns2,205 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes../../tools/verify_paper_audits.shruns21,578 bytes
Read SKILL.md
# Workflow 3: Paper Writing Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
patent-novelty-check
When your agent uses it
Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.
What it loads into context
Frontmatter
201 tokensAlways available to the agent
SKILL.md
1,656 tokensWhen the skill is activated
Reference documents
5,533 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore6,937 bytes../shared-references/patent-format-us.mddoc6,151 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Patent Novelty and Non-Obviousness Check
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Assess patentability of: **$ARGUMENTS**patent-pipeline
When your agent uses it
Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
3,707 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Patent Type Specifications
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Composing with Other Workflows
- Acknowledgements
Files
SKILL.mdcore15,255 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Patent Pipeline: From Invention to Filing
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Draft a complete patent application based on: **$ARGUMENTS**patent-review
When your agent uses it
Get an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.
What it loads into context
Frontmatter
196 tokensAlways available to the agent
SKILL.md
1,960 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Prerequisites
- Inputs
- Workflow
- Key Rules
Files
SKILL.mdcore7,904 bytesSKILL.mdcore7,904 bytesSKILL.mdcore7,904 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Patent Examiner Review via Codex MCP (xhigh reasoning)
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Get a multi-round patent examiner review of the patent application based on: **$ARGUMENTS**pixel-art
When your agent uses it
Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,609 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Design Principles
- Workflow
- Common Pitfalls
Files
SKILL.mdcore5,342 bytes
Read SKILL.md
# Pixel Art SVG Generator
Create a pixel art SVG illustration: $ARGUMENTS
## Design Principles
### Pixel Grid
- Each "pixel" is a `<rect>` with width/height of 7px
- Grid spacing: 7px (no gaps between pixels)
- Characters are typically 8-10 pixels wide, 8-12 pixels tall
- Use `<g transform="translate(x,y)">` to position and reuse character groups
### Color Palette
Keep it simple — 3-5 colors per character:prior-art-search
When your agent uses it
Search patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants to find relevant prior art.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,290 tokensWhen the skill is activated
Reference documents
1,373 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore5,538 bytes../shared-references/prior-art-databases.mddoc5,455 bytes
Read SKILL.md
# Prior Art Search
Search patents and literature for prior art relevant to: **$ARGUMENTS**
Adapted from `/research-lit` for patent-specific searching.
## Constants
- `MAX_PATENT_RESULTS = 20` — Maximum patent documents to analyze in detail
- `MAX_PAPER_RESULTS = 15` — Maximum academic papers to analyze in detail
- `SEARCH_YEARS = 10` — How many years back to search
- `PATENT_DATABASES = "google-patents, espacenet"` — Patent databases to search
## Inputsproof-checker
When your agent uses it
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
What it loads into context
Frontmatter
280 tokensAlways available to the agent
SKILL.md
14,164 tokensWhen the skill is activated
Reference documents
16,429 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- Reviewer Calling Convention
- Issue Taxonomy (20 categories, 4 groups)
- Two-Axis Severity System
- Side-Condition Checklists for Common Theorems
- Workflow
- Deep-Fix Mode (opt-in)
- Key Rules
- Output Files
- Submission Artifact Emission
- Example Invocations
Scripts executed separately
../../tools/research_wiki.py
Files
../lean-formalize/SKILL.mddoc22,797 bytesSKILL.mdcore56,673 bytesSKILL.mdcore56,673 bytesSKILL.mdcore56,673 bytesSKILL.mdcore56,673 bytesSKILL.mdcore56,673 bytesSKILL.mdcore56,673 bytesSKILL.mdcore56,673 bytesSKILL.mdcore56,673 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/fan-out-pattern.mddoc21,698 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Proof Checker: Rigorous Mathematical Verification & Fixing
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It isproof-orchestrator
When your agent uses it
Manage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
3,998 tokensWhen the skill is activated
Reference documents
10,859 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Untrusted-Content Rule
- Run Directory
- Continuing a Project
- Status Labels
- Notation Gate
- Derivation Structure Gate
- Workflow
- Optional DeepSeek Audit
- Manual Handoff Contract
- GPT Pro Output Repair
- Guardrails
Files
../lean-formalize/SKILL.mddoc22,797 bytesNOTICE.mddoc1,147 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesSKILL.mdcore18,956 bytesreferences/audit-output-contract.mddoc4,503 bytesreferences/deepseek-routing.mddoc3,479 bytesreferences/dispatch-prompts.mddoc7,841 bytesreferences/notation-audit.mddoc5,327 bytesreferences/proof-audit-rubric.mddoc4,430 bytesreferences/stress-tests.mddoc1,825 bytes
Read SKILL.md
# Proof Orchestrator
## Role
Run proof work as a local-first pipeline. The executor first attempts the proof, checks its correctness, and edits it for clarity and economy. Escalate the remaining hard obligation to GPT Pro.
Default escalation is manual: maintain the sources locally and give the user an exact browser-ready prompt. Invoking this skill does not authorize the executor to operate a browser, upload files, or spend API credit. An optional external `call-gpt-pro` skill may be used only when it is installed and the user explicitly asks the executor to perform the GPT Pro call for the current run.
An adversarial DeepSeek audit is an optional review mode inside this skill, not
a separate proof-checker. Run it only when the user explicitly requests
DeepSeek review or an independent second opinion for the current proof run.
Existing paper workflows continue to use ARIS's canonical `/proof-checker`;
do not replace that submission gate with this optional route.
proof-writer
When your agent uses it
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
1,809 tokensWhen the skill is activated
Reference documents
4,480 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Context: $ARGUMENTS
- Goal
- Inputs
- Workflow
- Required File Structure
- Output Modes
- Chat Response
- Key Rules
Files
../lean-formalize/SKILL.mddoc22,797 bytesSKILL.mdcore8,374 bytes
Read SKILL.md
# Proof Write: Rigorous Theorem / Lemma Drafting
Write a mathematically honest proof package, not a polished fake proof.
## Constants
- DEFAULT_PROOF_DOC = `PROOF_PACKAGE.md` in project root
- STATUS = `PROVABLE AS STATED | PROVABLE AFTER WEAKENING / EXTRA ASSUMPTION | NOT CURRENTLY JUSTIFIED`
## Context: $ARGUMENTS
## Goal
Produce exactly one of:qzcli
When your agent uses it
Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed training jobs on a Qizhi instance.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
2,315 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Environment contract
- Installation
- Configuration
- Quick Start
- Authentication
- Resource Discovery
- Check Available Nodes
- Job Submission
- Batch Submission
- Job Management
- Troubleshooting
Files
SKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytes../shared-references/compute-env-contract.mddoc10,567 bytes
Read SKILL.md
# qzcli — 启智平台任务管理
A kubectl/docker-style CLI for managing GPU compute jobs on the Qizhi (启智) platform.
**GitHub:** [tianyilt/qzcli_tool](https://github.com/tianyilt/qzcli_tool)
## Environment contract
Qizhi is the scheduler-cluster shape of `../shared-references/compute-env-contract.md`:
images are built OFF-platform and referenced at submit time, so the declarative
env spec + `env:<name>@<specHash>` ledger (`.aris/compute/qizhi.md`) is what
keeps "which image has which stack" answerable. Run the kernel witness inside a
submitted job (not on the login side) before trusting an image for a long run.
rebuttal
When your agent uses it
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
What it loads into context
Frontmatter
238 tokensAlways available to the agent
SKILL.md
6,130 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope
- Lifecycle Position
- Constants
- Reviewer Calling Convention
- Required Inputs
- Safety Model
- Workflow
- Key Rules
- Review Tracing
Files
SKILL.mdcore25,728 bytesSKILL.mdcore25,728 bytesSKILL.mdcore25,728 bytesSKILL.mdcore25,728 bytesSKILL.mdcore25,728 bytesSKILL.mdcore25,728 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Workflow 4: Rebuttal
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Prepare and maintain a grounded, venue-compliant rebuttal for: **$ARGUMENTS**render-html
When your agent uses it
Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.
What it loads into context
Frontmatter
262 tokensAlways available to the agent
SKILL.md
5,780 tokensWhen the skill is activated
Reference documents
21,637 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- Core invariants
- Tool Location
- Invocation
- Workflow
- What the helper supports
- Two-phase integration plan (Phase 1 was this skill; Phase 2 is workflow hooks, **activated 2026-05**)
- Customizing the templates
- External alternatives (for richer surfaces)
- Key rules
Scripts executed separately
scripts/render_html.py
Files
SKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesSKILL.mdcore22,895 bytesscripts/render_html.pyruns40,953 bytesscripts/templates/academic.htmlasset21,148 bytesscripts/templates/dashboard.htmlasset8,371 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-routing.mddoc52,492 bytes
Read SKILL.md
# /render-html: Markdown → single-file HTML for human reading
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Markdown is for writers. HTML is for readers.** ARIS workflow nodes write Markdown (canonical, audit-trail-friendly, machine-parseable). `/render-html` turns *selected* artifacts into a polished single-file HTML view for the human who actually has to read them. The Markdown stays the source of truth.research-implement-feature
When your agent uses it
Build a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BEFORE the code that depends on it and a cross-model sweep for the ones that slipped through undeclared. Use when user says "给我实现", "implement X", "帮我做一个能跑的", "先搭个原型再加功能", "build this feature", "prototype then extend", or hands over a capability description rather than an experiment plan.
What it loads into context
Frontmatter
299 tokensAlways available to the agent
SKILL.md
8,079 tokensWhen the skill is activated
Reference documents
27,067 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Two invariants
- Scope boundary
- Constants
- Interaction rule (HARD CONSTRAINT)
- Acceptance-gate provenance
- Artifacts
- The assumption ledger
- Stub discipline
- Phase 0 — Read the request, open the ledger
- Phase 1 — Build the feature ladder
- Phase 2 — F0, the spine
- Phase 3 — One rung at a time
- Phase 4 — Silent-assumption sweep (Type-B, cross-model)
- Phase 5 — Report
- Anti-patterns to refuse
- Worked example
- See Also
Files
SKILL.mdcore32,637 bytesSKILL.mdcore32,637 bytesSKILL.mdcore32,637 bytesSKILL.mdcore32,637 bytesSKILL.mdcore32,637 bytes../shared-references/acceptance-gate.mddoc16,967 bytes../shared-references/capture-antipatterns.mddoc4,516 bytes../shared-references/effort-contract.mddoc8,352 bytes../shared-references/injection-hygiene.mddoc7,468 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/review-scope-limits.mddoc4,174 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc3,473 bytes../shared-references/reviewer-routing.mddoc52,492 bytes
Read SKILL.md
# Research Implement: Feature
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Build: **$ARGUMENTS**research-lit
When your agent uses it
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
11,998 tokensWhen the skill is activated
Reference documents
20,024 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Data Sources
- Workflow
- Key Rules
Scripts executed separately
../../tools/arxiv_fetch.py../../tools/deepxiv_fetch.py../../tools/exa_search.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/openalex_fetch.py../../tools/research_wiki.py../../tools/semantic_scholar_fetch.py../../tools/skill_picker.py../../tools/verify_papers.py
Files
SKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytesSKILL.mdcore45,319 bytes../shared-references/citation-discipline.mddoc20,131 bytes../shared-references/fan-out-pattern.mddoc21,698 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/output-composition.mddoc5,005 bytes../shared-references/wiki-helper-resolution.mddoc6,503 bytes../../tools/arxiv_fetch.pyruns11,762 bytes../../tools/deepxiv_fetch.pyruns6,222 bytes../../tools/exa_search.pyruns14,437 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/openalex_fetch.pyruns12,106 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/semantic_scholar_fetch.pyruns14,381 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes../../tools/verify_papers.pyruns29,634 bytes
Read SKILL.md
# Research Literature Review
Research topic: $ARGUMENTS
## Constants
- **PAPER_LIBRARY** — Local directory containing user's paper collection (PDFs). Check these paths in order:
1. `papers/` in the current project directory
2. `literature/` in the current project directory
3. Custom path specified by user in `CLAUDE.md` under `## Paper Library`
- **MAX_LOCAL_PAPERS = 20** — Maximum number of local PDFs to scan (read first 3 pages each). If more are found, prioritize by filename relevance to the topic.
- **SOURCES = `all`** — Which literature sources to search. Options: `zotero`, `obsidian`, `local`, `web`, `semantic-scholar`, `deepxiv`, `exa`, `gemini`, `openalex`, `all`. Full source table and selection rules: see `## Data Sources` below.
- **ARXIV_DOWNLOAD = false** — When `true`, download top 3-5 most relevant arXiv PDFs to PAPER_LIBRARY after search. When `false` (default), only fetch metadata (title, abstract, authors) via arXiv API — no files are downloaded.research-pipeline
When your agent uses it
Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
6,019 tokensWhen the skill is activated
Reference documents
15,301 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Optional formal proof route
- Constants
- Checkpoint execution rule
- Overview
- Resumable runs (`— resume <run_id>`)
- Overnight heartbeat: stall detection → forced structural pivot
- Pipeline
- Render HTML view (auto, when `RENDER_HTML = true`)
- Output Protocols
- Key Rules
- Typical Timeline
Scripts executed separately
../../tools/iteration_log.py../../tools/run_state.py
Files
../lean-formalize/SKILL.mddoc22,797 bytesSKILL.mdcore24,299 bytesSKILL.mdcore24,299 bytesSKILL.mdcore24,299 bytesSKILL.mdcore24,299 bytesSKILL.mdcore24,299 bytesSKILL.mdcore24,299 bytesSKILL.mdcore24,299 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/resumable-runs.mddoc6,694 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../tools/iteration_log.pyruns5,588 bytes../../tools/run_state.pyruns18,500 bytes
Read SKILL.md
# Full Research Pipeline: Idea → Experiments → Submission
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> ⏱ **External cadence: non-judgmental heartbeat only.** An overnight `/loop` /research-refine
When your agent uses it
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
What it loads into context
Frontmatter
242 tokensAlways available to the agent
SKILL.md
8,059 tokensWhen the skill is activated
Reference documents
4,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- State Persistence (Checkpoint Recovery)
- Output Structure
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
SKILL.mdcore34,664 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Research Refine: Problem-Anchored, Elegant, Frontier-Aware Plan Refinement
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Refine and concretize: **$ARGUMENTS**research-refine-pipeline
When your agent uses it
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,635 tokensWhen the skill is activated
Reference documents
14,741 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Rule
- Default Outputs
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../experiment-plan/SKILL.mddoc9,728 bytesSKILL.mdcore7,020 bytes../research-refine/SKILL.mddoc34,664 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc2,354 bytes../shared-references/output-versioning.mddoc4,807 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Research Refine Pipeline: End-to-End Method and Experiment Planning
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Refine and concretize: **$ARGUMENTS**research-review
When your agent uses it
Get a deep critical review of research from a selected reviewer (Codex by default, Gemini, Grok, Claude Code, or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
What it loads into context
Frontmatter
225 tokensAlways available to the agent
SKILL.md
3,233 tokensWhen the skill is activated
Reference documents
7,926 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Reviewer Calling Convention
- Context: $ARGUMENTS
- Prerequisites
- Workflow
- Key Rules
- Prompt Templates
- Review Tracing
Files
SKILL.mdcore13,815 bytesSKILL.mdcore13,815 bytesSKILL.mdcore13,815 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/output-composition.mddoc5,005 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Research Review via External Reviewer Backend (ultra reasoning)
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is
> verdict-bearing — it produces a cross-model review verdict, multi-round with
> reviewer thread continuity. An external timer re-fires the verdict on
> wall-clock time and breaks the reviewer's round-to-round memory: zero new
> signal, full token cost. Schedule the *external wait that precedes it* (work
> ready → then review once), not the verdict. See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
Get a multi-round critical review of research work from the selected external reviewer backend with maximum reasoning depth.
## Constants
research-wiki
When your agent uses it
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
5,408 tokensWhen the skill is activated
Reference documents
8,066 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Wiki Directory Structure
- Subcommands
- Helper resolution (run before any subcommand below)
- Integration with Existing Workflows
- Re-ideation Trigger
- Key Rules
- Acknowledgements
Scripts executed separately
../../tools/capture_filter.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/research_wiki.py../../tools/skill_picker.py../../tools/smart_update.sh../../tools/smart_update.sh../../tools/smart_update.sh../../tools/smart_update.sh../../tools/smart_update.sh../../tools/smart_update.sh../../tools/smart_update.sh../../tools/smart_update.sh
Files
SKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytesSKILL.mdcore20,553 bytes../shared-references/capture-antipatterns.mddoc4,516 bytes../shared-references/integration-contract.mddoc26,858 bytes../../tools/capture_filter.pyruns6,080 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes../../tools/smart_update.shruns22,932 bytes../../tools/smart_update.shruns22,932 bytes../../tools/smart_update.shruns22,932 bytes../../tools/smart_update.shruns22,932 bytes../../tools/smart_update.shruns22,932 bytes../../tools/smart_update.shruns22,932 bytes../../tools/smart_update.shruns22,932 bytes../../tools/smart_update.shruns22,932 bytes
Read SKILL.md
# Research Wiki: Persistent Research Knowledge Base
Subcommand: **$ARGUMENTS**
## Overview
The research wiki is a persistent, per-project knowledge base that accumulates structured knowledge across the entire ARIS research lifecycle. Unlike one-off literature surveys that are used and forgotten, the wiki **compounds** — every paper read, idea tested, experiment run, and review received makes the wiki smarter.
Inspired by [Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): compile knowledge once, keep it current, don't re-derive on every query.
## Core Concepts
### Four Entity Types
resubmit-pipeline
When your agent uses it
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says "resubmit pipeline", "重投流程", "port paper to <new venue>", "resubmit to <venue>", "tighten paper for resubmission", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.
What it loads into context
Frontmatter
176 tokensAlways available to the agent
SKILL.md
8,712 tokensWhen the skill is activated
Reference documents
6,478 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- When to Use
- When NOT to Use
- Constants
- Inputs
- Pipeline
- Page-Shrink Heuristic
- Convergence Criteria (Phase 2 stop condition)
- Master `RESUBMIT_REPORT.md` Ledger
- Failure Modes
- Key Rules
- Output Contract
- Review Tracing
- Notes
Files
../integrity-forensics/SKILL.mddoc17,170 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytesSKILL.mdcore34,242 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Resubmit Pipeline: Text-Only Microedit Mode
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Compose a polished paper into a new venue under text-only constraints: **$ARGUMENTS**result-to-claim
When your agent uses it
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
What it loads into context
Frontmatter
210 tokensAlways available to the agent
SKILL.md
4,581 tokensWhen the skill is activated
Reference documents
9,412 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- When to Use
- Workflow
- Rules
- Review Tracing
Scripts executed separately
../../tools/evidence_check.py../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/skill_picker.py
Files
SKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytesSKILL.mdcore17,854 bytes../shared-references/evidence-precheck.mddoc3,248 bytes../shared-references/external-cadence.mddoc19,084 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/wiki-helper-resolution.mddoc6,503 bytes../../tools/evidence_check.pyruns9,970 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Result-to-Claim Gate
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It isrun-experiment
When your agent uses it
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
3,437 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Rules
- CLAUDE.md Example
Files
SKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytesSKILL.mdcore12,848 bytes../shared-references/compute-env-contract.mddoc10,567 bytes
Read SKILL.md
# Run Experiment
Deploy and run ML experiment: $ARGUMENTS
## Workflow
### Step 1: Detect Environment
Read the project's `CLAUDE.md` to determine the experiment environment:
- **Local GPU** (`gpu: local`): Look for local CUDA/MPS setup info
- **Remote server** (`gpu: remote`): Look for SSH alias, conda env, code directory
- **Vast.ai** (`gpu: vast`): Check for `vast-instances.json` at project root — if a running instance exists, use it. Also check `CLAUDE.md` for a `## Vast.ai` section.
- **Modal** (`gpu: modal`): Serverless GPU via Modal. No SSH, no Docker, auto scale-to-zero. Delegate to `/serverless-modal`.semantic-scholar
When your agent uses it
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
3,127 tokensWhen the skill is activated
Reference documents
8,788 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Workflow
- Key Rules
Scripts executed separately
../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/install_aris.sh../../tools/research_wiki.py../../tools/semantic_scholar_fetch.py../../tools/skill_picker.py
Files
SKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytesSKILL.mdcore10,943 bytes../shared-references/integration-contract.mddoc26,858 bytes../shared-references/wiki-helper-resolution.mddoc6,503 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/install_aris.shruns80,107 bytes../../tools/research_wiki.pyruns78,927 bytes../../tools/semantic_scholar_fetch.pyruns14,381 bytes../../tools/skill-groups.tsvasset9,410 bytes../../tools/skill_picker.pyruns8,880 bytes
Read SKILL.md
# Semantic Scholar Paper Search
Search topic or paper ID: $ARGUMENTS
## Role & Positioning
This skill is the **published venue** counterpart to `/arxiv`:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |
| `/semantic-scholar` | Semantic Scholar API | **Published** journal/conference papers (IEEE, ACM, Springer, etc.) with citation counts, venue info, TLDR |
**Do NOT duplicate arXiv's job.** If results contain an `externalIds.ArXiv` field, the paper is also on arXiv — note this but do not re-fetch from arXiv.serverless-modal
When your agent uses it
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
3,532 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Authentication
- Pricing (source: modal.com/pricing, per-second billing)
- !! Cost Estimation Required !!
- Workflow
- CLI Reference
- Key Tips
- Composing with Other Skills
- CLAUDE.md Example
- Documentation
Files
SKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytesSKILL.mdcore13,161 bytes../shared-references/compute-env-contract.mddoc10,567 bytes
Read SKILL.md
# Modal Cloud GPU — Training & Inference
Task: $ARGUMENTS
## Overview
**Modal** is a serverless GPU cloud. Key advantages over SSH-based platforms (vast.ai, remote servers):
- **Zero config**: no SSH, no Docker, no port forwarding. Write Python → `modal run` → done.
- **Auto scale-to-zero**: billing stops the instant your code finishes. No idle instances.
- **Local-first**: run `modal run` from your laptop. Code, data, and results stay local; only the GPU function runs remotely.
- **Reproducible environments**: dependencies declared in code via `modal.Image`, not system-level packages.
Treat the `modal.Image` chain as the RENDERED form of the declarative env spec in
`../shared-references/compute-env-contract.md` — same spec fields (base, ordered
pip phases, env vars, smoke probes), same `env:<name>@<specHash>` ledger entry inauto-paper-improvement-loop
When your agent uses it
Autonomously improve a generated paper via Claude review through claude-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
8,756 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Constants
- Optional: Edit Whitelist (`— edit-whitelist <path>`, opt-in)
- Inputs
- State Persistence (Compact Recovery)
- Reviewer Independence Protocol
- Workflow
- Output
- Key Rules
- Typical Score Progression
- Review Tracing
Files
SKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytesSKILL.mdcore36,359 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Auto Paper Improvement Loop: Review → Fix → Recompile
Autonomously improve the paper at: **$ARGUMENTS**
## Contextauto-review-loop
When your agent uses it
Autonomous multi-round research review loop. Repeatedly reviews using Claude Code via claude-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
7,309 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- Claude-Aligned Reviewer Memory and Debate
- Instructions
- State Persistence (Compact Recovery)
- Workflow
- Your Reviewer Memory (persistent across rounds)
- Review Tracing
- Output Protocols
- Key Rules
- Prompt Template for Round 2+
- Acquittal Gate Test Specifications
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore30,452 bytesSKILL.mdcore30,452 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Auto Review Loop: Autonomous Research Improvement
> **Claude overlay assurance:** this route is a different model family from the Codex executor and records `review_independence: cross-family` plus `acceptance_status: accepted`.
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.novelty-check
When your agent uses it
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
1,617 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Instructions
- Review Tracing
Files
SKILL.mdcore6,788 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Novelty Check Skill
Check whether a proposed method/idea has already been done in the literature: **$ARGUMENTS**
## Constantspaper-figure
When your agent uses it
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
3,676 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope: What This Skill Can and Cannot Do
- Constants
- Inputs
- Workflow
- Output
- Key Rules
- Figure Type Reference
- Acknowledgements
Files
SKILL.mdcore14,208 bytesSKILL.mdcore14,208 bytesSKILL.mdcore14,208 bytesSKILL.mdcore14,208 bytesSKILL.mdcore14,208 bytesSKILL.mdcore14,208 bytesSKILL.mdcore14,208 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Paper Figure: Publication-Quality Plots from Experiment Data
Generate all figures and tables for a paper based on: **$ARGUMENTS**
## Scope: What This Skill Can and Cannot Dopaper-plan
When your agent uses it
Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
3,260 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Orchestra-Guided Writing Overlay
- Workflow
- Key Rules
- Acknowledgements
- Output Protocols
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore13,183 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Paper Plan: From Review Conclusions to Paper Outline
Generate a structured, section-by-section paper outline from: **$ARGUMENTS**
## Constantspaper-write
When your agent uses it
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
6,608 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Orchestra-Guided Writing Overlay
- Templates
- Workflow
- Key Rules
- Writing Quality Reference
- Acknowledgements
Files
SKILL.mdcore27,669 bytesSKILL.mdcore27,669 bytesSKILL.mdcore27,669 bytesSKILL.mdcore27,669 bytesSKILL.mdcore27,669 bytesSKILL.mdcore27,669 bytesSKILL.mdcore27,669 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Paper Write: Section-by-Section LaTeX Generation
Draft a LaTeX paper based on: **$ARGUMENTS**
## Constantsresearch-refine
When your agent uses it
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative Claude review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
7,330 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- State Persistence (Checkpoint Recovery)
- Output Structure
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore32,172 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Research Refine: Problem-Anchored, Elegant, Frontier-Aware Plan Refinement
Refine and concretize: **$ARGUMENTS**
## Overviewresearch-review
When your agent uses it
Get a deep critical review of research from Claude via claude-review MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
2,117 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Context: $ARGUMENTS
- Prerequisites
- Workflow
- Key Rules
- Prompt Templates
Files
SKILL.mdcore9,509 bytesSKILL.mdcore9,509 bytesSKILL.mdcore9,509 bytes
Read SKILL.md
> Override for Codex users who want **Claude Code**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
>
> This reviewer is a different model family from the Codex executor. Every overlay trace/audit records:
>
> ```yaml
> review_independence: cross-family
> acceptance_status: accepted
> ```
# Research Review via `claude-review` MCP (high-rigor review)
> **Claude overlay assurance:** this route is a different model family from the Codex executor and records `review_independence: cross-family` plus `acceptance_status: accepted`.
Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.auto-paper-improvement-loop
When your agent uses it
Autonomously improve a generated paper via Gemini review through gemini-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
4,143 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Constants
- Inputs
- State Persistence (Compact Recovery)
- Workflow
- Output
- Output Protocols
- Key Rules
- Typical Score Progression
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytesSKILL.mdcore17,170 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Auto Paper Improvement Loop: Review → Fix → Recompile
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Autonomously improve the paper at: **$ARGUMENTS**
## Context
This skill is designed to run **after** Workflow 3 (`/paper-plan` → `/paper-figure` → `/paper-write` → `/paper-compile`). It takes a compiled paper and iteratively improves it through external LLM review.
Unlike `/auto-review-loop` (which iterates on **research** — running experiments, collecting data, rewriting narrative), this skill iterates on **paper writing quality** — fixing theoretical inconsistencies, softening overclaims, adding missing content, and improving presentation.
auto-review-loop
When your agent uses it
Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
3,526 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- State Persistence (Compact Recovery)
- Workflow
- Output Protocols
- Key Rules
- Prompt Template for Round 2+
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore15,066 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Auto Review Loop: Autonomous Research Improvement
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
## Context: $ARGUMENTS
## Constants
- MAX_ROUNDS = 4
- POSITIVE_THRESHOLD: score >= 6/10 AND verdict ∈ {"ready", "almost"} — both must hold, matching the operative STOP CONDITION below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used "or" + a stale verdict set; the AND form is authoritative.)grant-proposal
When your agent uses it
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
7,653 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Grant Type Specifications
- State Persistence (Compact Recovery)
- Workflow
- Output Protocols
- Key Rules
- Parameter Pass-Through
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore31,605 bytesSKILL.mdcore31,605 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Grant Proposal: From Research Ideas to Fundable Application
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Draft a grant proposal based on: **$ARGUMENTS**
## Overview
This skill turns validated research ideas into a structured, reviewer-ready grant proposal. It chains sub-skills into a grant-specific pipeline:
```
/research-lit → /novelty-check → [structure design] → [draft] → /research-review → [revise] → GRANT_PROPOSAL.mdidea-creator
When your agent uses it
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
3,791 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore16,164 bytesSKILL.mdcore16,164 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Research Idea Creator
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Generate publishable research ideas for: $ARGUMENTS
## Overview
Given a broad research direction from the user, systematically generate, validate, and rank concrete research ideas. Standalone, Phase 1's landscape survey is **inline** (WebSearch — it does not invoke `/research-lit`); Phases 4-5 invoke `/novelty-check`, `/run-experiment`, and `/monitor-experiment` for validation and pilots. For the full sub-skill pipeline (`/research-lit` → idea generation → `/novelty-check` → `/research-review`), run `/idea-discovery` (Workflow 1), which orchestrates this skill.
## Constants
idea-discovery
When your agent uses it
Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says \"找idea全流程\", \"idea discovery pipeline\", \"从零开始找方向\", or wants the complete idea exploration workflow.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
3,092 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Checkpoint execution rule
- Pipeline
- Output Protocols
- Key Rules
- Composing with Workflow 2
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore12,967 bytesSKILL.mdcore12,967 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Workflow 1: Idea Discovery Pipeline
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Orchestrate a complete idea discovery workflow for: **$ARGUMENTS**
## Overview
This skill chains sub-skills into a single automated pipeline:
```
/research-lit → /idea-creator → /novelty-check → /research-review → /research-refine-pipelineidea-discovery-robot
When your agent uses it
Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says \"robotics idea discovery\", \"机器人找idea\", \"embodied AI idea\", \"机器人方向探索\", \"sim2real 选题\", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
3,449 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Execution Rule
- Phase 0: Frame the Robotics Problem
- Phase 1: Robotics Literature Survey
- Phase 2: Robotics-Specific Idea Generation and Filtering
- Phase 3: Feasibility and Pilot Design
- Phase 4: Deep Novelty Verification
- Phase 5: External Robotics Review
- Phase 6: Final Report
- Output Protocols
- Key Rules
- Composing with Later Work
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore15,426 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Robotics Idea Discovery Pipeline
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Orchestrate a robotics-specific idea discovery workflow for: **$ARGUMENTS**
## Overview
This skill chains four sub-skills into a single automated pipeline:
```
/research-lit → /idea-creator (robotics framing) → /novelty-check → /research-reviewnovelty-check
When your agent uses it
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
1,457 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Instructions
Files
SKILL.mdcore6,110 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Novelty Check Skill
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Check whether a proposed method/idea has already been done in the literature: **$ARGUMENTS**
## Constants
- **REVIEWER_MODEL = `gemini-review`** — Gemini reviewer invoked through the local `gemini-review` MCP bridge. Set `GEMINI_REVIEW_MODEL` if you need a specific Gemini model override.
## Instructions
paper-figure
When your agent uses it
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
3,275 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope: What This Skill Can and Cannot Do
- Constants
- Inputs
- Workflow
- Output
- Output Protocols
- Key Rules
- Figure Type Reference
- Acknowledgements
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore12,514 bytesSKILL.mdcore12,514 bytesSKILL.mdcore12,514 bytesSKILL.mdcore12,514 bytesSKILL.mdcore12,514 bytesSKILL.mdcore12,514 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Paper Figure: Publication-Quality Plots from Experiment Data
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Generate all figures and tables for a paper based on: **$ARGUMENTS**
## Scope: What This Skill Can and Cannot Do
| Category | Can auto-generate? | Examples |
|----------|-------------------|----------|
| **Data-driven plots** | ✅ Yes | Line plots (training curves), bar charts (method comparison), scatter plots, heatmaps, box/violin plots |
| **Comparison tables** | ✅ Yes | LaTeX tables comparing prior bounds, method features, ablation results |paper-plan
When your agent uses it
Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
2,754 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Workflow
- Output Protocols
- Key Rules
- Acknowledgements
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore10,966 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Paper Plan: From Review Conclusions to Paper Outline
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Generate a structured, section-by-section paper outline from: **$ARGUMENTS**
## Constants
- **REVIEWER_MODEL = `gemini-review`** — Gemini reviewer invoked through the local `gemini-review` MCP bridge. Set `GEMINI_REVIEW_MODEL` if you need a specific Gemini model override.
- **TARGET_VENUE = `ICLR`** — Default venue. User can override (e.g., `/paper-plan "topic" — venue: NeurIPS`). Supported: `ICLR`, `NeurIPS`, `ICML`.
- **MAX_PAGES** — Main body page limit, measured from first page to end of Conclusion section (excluding references, appendix, and acknowledgements). ICLR=9, NeurIPS=9, ICML=8.
paper-poster-html
When your agent uses it
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster.
What it loads into context
Frontmatter
188 tokensAlways available to the agent
SKILL.md
1,292 tokensWhen the skill is activated
Reference documents
6,101 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Reviewer constants (overlay)
- Phase 1 step 2 — Cross-model content audit (Gemini)
- Phase 6 — Final review (Gemini, multimodal)
- Review tracing
Files
../../shared-references/review-tracing.mddoc23,757 bytesSKILL.mdcore5,157 bytesSKILL.mdcore5,157 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex/Codex-MCP reviewer, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Paper Poster (HTML): measurement-gated poster generation
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
One HTML file styled for an exact print canvas (`@page { size: W H }`), rendered to PDF
via Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen
preview lies; only print emulation at the correct viewport tells the truth. Core gate
machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, ©
2026 Ruishuo Chen — see `NOTICE.md` and `LICENSES/posterly-MIT.txt` in the mainline
skill directory); ARIS adds style discipline gates, figure-provenance gates, the
cross-model review loop, and the anti-patch-loop fix vocabulary.
paper-slides
When your agent uses it
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
5,666 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Constants
- Talk Type → Slide Count
- Venue Color Schemes
- State Persistence (Compact Recovery)
- Workflow
- Output Protocols
- Key Rules
- Parameter Pass-Through
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytesSKILL.mdcore20,305 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a Codex-MCP reviewer, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Paper Slides: From Paper to Conference Talk
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Generate conference presentation slides from: **$ARGUMENTS**
## Context
This skill runs **after** Workflow 3 (`/paper-writing`). It takes a compiled paper and generates a presentation slide deck for conference oral talks, spotlight presentations, or poster lightning talks.
Unlike posters (single page, visual-first), slides tell a **temporal story**: each slide builds on the previous one, with progressive revelation of the research narrative. A good talk makes the audience understand *why this matters* before showing *what was done*.
paper-write
When your agent uses it
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
5,308 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Templates
- Workflow
- Output Protocols
- Key Rules
- Writing Quality Reference
- Acknowledgements
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore22,091 bytesSKILL.mdcore22,091 bytesSKILL.mdcore22,091 bytesSKILL.mdcore22,091 bytesSKILL.mdcore22,091 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Paper Write: Section-by-Section LaTeX Generation
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Draft a LaTeX paper based on: **$ARGUMENTS**
## Constants
- **REVIEWER_MODEL = `gemini-review`** — Gemini reviewer invoked through the local `gemini-review` MCP bridge. Set `GEMINI_REVIEW_MODEL` if you need a specific Gemini model override.
- **TARGET_VENUE = `ICLR`** — Default venue. Supported: `ICLR`, `NeurIPS`, `ICML`. Determines style file and formatting.
- **ANONYMOUS = true** — If true, use anonymous author block. Set `false` for camera-ready.
- **MAX_PAGES = 9** — Main body page limit. Counts from first page to end of Conclusion section. References and appendix are NOT counted.paper-writing
When your agent uses it
Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says \"写论文全流程\", \"write paper pipeline\", \"从报告到PDF\", \"paper writing\", or wants the complete paper generation workflow.
What it loads into context
Frontmatter
135 tokensAlways available to the agent
SKILL.md
3,296 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Inputs
- Pipeline
- Output Protocols
- Key Rules
- Composing with Other Workflows
- Typical Timeline
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore13,387 bytesSKILL.mdcore13,387 bytesSKILL.mdcore13,387 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Workflow 3: Paper Writing Pipeline
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Orchestrate a complete paper writing workflow for: **$ARGUMENTS**
## Overview
This skill chains five sub-skills into a single automated pipeline:
```
/paper-plan → /paper-figure → /paper-write → /paper-compile → /auto-paper-improvement-loopresearch-refine
When your agent uses it
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative Gemini review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
6,582 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Output Structure
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore29,410 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Research Refine: Problem-Anchored, Elegant, Frontier-Aware Plan Refinement
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Refine and concretize: **$ARGUMENTS**
## Overview
Use this skill when the research problem is already visible but the technical route is still fuzzy. The goal is not to produce a bloated proposal or a benchmark shopping list. The goal is to turn a vague direction into a **problem -> focused method -> minimal validation** document that is concrete enough to implement, elegant enough to feel paper-worthy, and current enough to resonate in the foundation-model era.
Four principles dominate this skill:
research-review
When your agent uses it
Get a deep critical review of research from Gemini via gemini-review MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
1,616 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Context: $ARGUMENTS
- Prerequisites
- Workflow
- Key Rules
- Prompt Templates
Files
SKILL.mdcore7,273 bytesSKILL.mdcore7,273 bytesSKILL.mdcore7,273 bytes
Read SKILL.md
> Override for Codex users who want **Gemini**, not a second Codex agent, to act as the reviewer. Install this package **after** `skills/skills-codex/*`.
# Research Review via `gemini-review` MCP (high-rigor review)
> **Gemini overlay assurance:** `review_independence: cross-family` and `acceptance_status: accepted`.
Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.
## Constants
- **REVIEWER_MODEL = `gemini-review`** — Gemini reviewer invoked through the local `gemini-review` MCP bridge. Set `GEMINI_REVIEW_MODEL` if you need a specific Gemini model override.
## Context: $ARGUMENTS
ablation-planner
When your agent uses it
Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,216 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- When to Use
- Workflow
- Rules
Files
SKILL.mdcore5,416 bytes
Read SKILL.md
# Ablation Planner
Systematically design ablation studies that answer the questions reviewers will ask. The reviewer agent leads the design; the local executor reviews feasibility and implements.
## Context: $ARGUMENTS
## When to Use
- Main results pass `/result-to-claim` with `claim_supported = yes` or `partial`
- The user explicitly requests ablation planning
- `/auto-review-loop` identifies missing ablations
## Workflow
alphaxiv
When your agent uses it
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
2,392 tokensWhen the skill is activated
Reference documents
5,148 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Workflow
- Key Rules
- Integration with Other Skills
Scripts executed separately
../../../tools/research_wiki.py
Files
SKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytesSKILL.mdcore8,809 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# AlphaXiv Paper Lookup
Lookup paper: $ARGUMENTS
> Quick single-paper reader with tiered source fallback (overview → full markdown → LaTeX source). Powered by [AlphaXiv](https://www.alphaxiv.org).
## Role & Positioning
This skill is the **quick single-paper reader** that returns LLM-optimized summaries:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Batch search, PDF download, metadata |
| `/deepxiv` | DeepXiv SDK | Progressive section-level reading |analyze-results
When your agent uses it
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
352 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Output Format
Files
SKILL.mdcore1,568 bytes
Read SKILL.md
# Analyze Experiment Results
Analyze: $ARGUMENTS
## Workflow
### Step 1: Locate Results
Find all relevant JSON/CSV result files:
- Check `figures/`, `results/`, or project-specific output directories
- Parse JSON results into structured data
### Step 2: Build Comparison Table
Organize results by:
- **Independent variables**: model type, hyperparameters, data configarxiv
When your agent uses it
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
2,235 tokensWhen the skill is activated
Reference documents
5,148 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Workflow
- Key Rules
Scripts executed separately
../../../tools/arxiv_fetch.py
Files
SKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytesSKILL.mdcore7,808 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/arxiv_fetch.pyruns11,762 bytes
Read SKILL.md
# arXiv Paper Search & Download
Search topic or arXiv paper ID: $ARGUMENTS
## Constants
- **PAPER_DIR** - Local directory to save downloaded PDFs. Default: `papers/` in the current project directory.
- **MAX_RESULTS = 10** - Default number of search results.
- **ARXIV_FETCHER** — canonical name `arxiv_fetch.py`, resolved per
[`shared-references/integration-contract.md`](../shared-references/integration-contract.md) §2
(Codex-side chain: `$ARIS_REPO/tools/` → `tools/` → `~/.codex/skills/arxiv/`).
Policy D1 — if unresolved (canonical chain exhausted), fall back to inline Python.
> Overrides (append to arguments):auto-paper-improvement-loop
When your agent uses it
Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
What it loads into context
Frontmatter
216 tokensAlways available to the agent
SKILL.md
8,953 tokensWhen the skill is activated
Reference documents
8,335 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Constants
- Optional: Edit Whitelist (`— edit-whitelist <path>`, opt-in)
- Inputs
- State Persistence (Compact Recovery)
- Reviewer Independence Protocol
- Workflow
- Output
- Key Rules
- Typical Score Progression
- Review Tracing
Files
SKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytesSKILL.mdcore37,137 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/writing-principles.mddoc17,539 bytes
Read SKILL.md
# Auto Paper Improvement Loop: Review → Fix → Recompile
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
auto-review-loop
When your agent uses it
Autonomous multi-round research review loop. Uses a fresh Codex agent or selected Gemini, Grok, or Claude Code reviewer, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
7,758 tokensWhen the skill is activated
Reference documents
9,729 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- Claude-Aligned Reviewer Memory and Debate
- Instructions
- State Persistence (Compact Recovery)
- Workflow
- Your Reviewer Memory (persistent across rounds)
- Review Tracing
- Output Protocols
- Key Rules
- Prompt Template for Round 2+
- Acquittal Gate Test Specifications
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore32,654 bytesSKILL.mdcore32,654 bytesSKILL.mdcore32,654 bytes../shared-references/review-scope-limits.mddoc4,174 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-routing.mddoc8,348 bytes
Read SKILL.md
# Auto Review Loop: Autonomous Research Improvement
> **Codex assurance:** the default same-family reviewer result records
> `review_independence: same-family` and `acceptance_status: provisional` in its
> trace/state artifact. A positive provisional verdict may drive fixes and stop
> the loop, but is never cross-family accepted. A selected reviewer earns
> cross-family acceptance only from its actual models and completed in-scope
> positive review. Reviewer failure emits BLOCKED.
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
## Context: $ARGUMENTS
## Constantsauto-review-loop-llm
When your agent uses it
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
2,308 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- LLM Configuration
- API Call Method
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Prompt Template for Round 2+
- Output Protocols
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore8,324 bytesSKILL.mdcore8,324 bytesSKILL.mdcore8,324 bytesSKILL.mdcore8,324 bytes
Read SKILL.md
# Auto Review Loop (Generic LLM): Autonomous Research Improvement
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
## Context: $ARGUMENTS
## Constants
- MAX_ROUNDS = 4
- POSITIVE_THRESHOLD: score >= 6/10 AND verdict ∈ {"ready", "almost"} — both must hold, matching the operative STOP CONDITION below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used "or" + a stale verdict set; the AND form is authoritative.)
- REVIEW_DOC: `review-stage/AUTO_REVIEW.md` (cumulative log) *(fall back to `./AUTO_REVIEW.md` for legacy projects)*
## LLM Configuration
auto-review-loop-minimax
When your agent uses it
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
3,017 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- API Configuration
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Prompt Template for Round 2+
- Output Protocols
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore12,132 bytesSKILL.mdcore12,132 bytesSKILL.mdcore12,132 bytesSKILL.mdcore12,132 bytes
Read SKILL.md
# Auto Review Loop (MiniMax Version): Autonomous Research Improvement
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
## Context: $ARGUMENTS
## Constants
- MAX_ROUNDS = 4
- POSITIVE_THRESHOLD: score >= 6/10 AND verdict ∈ {"ready", "almost"} — both must hold, matching the operative STOP CONDITION below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used "or" + a stale verdict set; the AND form is authoritative.)
- REVIEW_DOC: `review-stage/AUTO_REVIEW.md` (cumulative log) *(fall back to `./AUTO_REVIEW.md` for legacy projects)*
- REVIEWER_MODEL = `MiniMax-M3` — Model used via MiniMax API
## API Configurationcitation-audit
When your agent uses it
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
What it loads into context
Frontmatter
229 tokensAlways available to the agent
SKILL.md
7,744 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- What This Skill Catches
- Constants
- Workflow
- Uncited Entry Detection (opt-in)
- Key Rules
- Comparison with Other Audit Skills
- Known Limitations
- Review Tracing
- Output Contract
- Optional: Soft-Only Mode (— soft-only)
- Submission Artifact Emission
- See Also
Files
SKILL.mdcore31,886 bytesSKILL.mdcore31,886 bytesSKILL.mdcore31,886 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Citation Audit
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Codex assurance:** base audit artifacts recordcitation-crosscheck
When your agent uses it
Conditionally double-blind bibliographic cross-check (double-blind only when the host can isolate the web agent; a flag-only heuristic when isolation can't be attested): one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web while blind to the .bib, and a third extractor emits a mechanical field-by-field delta to catch dropped/re-ordered authors, wrong years, wrong venues, and bad DOIs/arXiv ids. The main agent (never a shard) assigns the MATCH/MINOR/MISMATCH verdict per reference, and exports a side-by-side spreadsheet. Use when user says "citation crosscheck", "double-blind citation check", "verify bib against scholar", "bib field audit", "引用交叉核对", or before submission when bibliography FIELD accuracy (not just existence) must be certified.
What it loads into context
Frontmatter
238 tokensAlways available to the agent
SKILL.md
10,497 tokensWhen the skill is activated
Reference documents
19,871 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this exists (and how it differs from `citation-audit`)
- Constants
- Workflow
- Key rules
Scripts executed separately
scripts/cx_verify.py
Files
SKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesSKILL.mdcore38,756 bytesscripts/cx_verify.pyruns84,510 bytes../shared-references/acceptance-gate.mddoc19,333 bytes../shared-references/external-cadence.mddoc20,174 bytes../shared-references/fan-out-pattern.mddoc23,134 bytes../shared-references/integration-contract.mddoc19,930 bytes
Read SKILL.md
# Citation Cross-Check (conditionally double-blind bib-vs-web field audit)
> **Codex mirror adaptation (normative).** This skill has no cross-model jury *by
> design* — it is an evidence instrument, not an acquittal step (see the acceptance-gate
> note in Step 2, and pair it with `citation-audit` for the cross-model verdict). A and B
> are read-only extraction shards and C emits a mechanical per-field delta, so every
> verdict is assigned by the main agent from that delta plus its own primary-source
> fetch — not by any shard and not by a reviewer model.
>
> **Blindness is NOT automatically identical across hosts — it is *conditional on
> isolation*, and the gate enforces that.** The whole cross-check rests on B never seeing
> the `.bib`. On the mainline, the `Agent` tool gives B a fresh context. On a Codex host
> the frontmatter grants **no delegation tool** (no `Agent`, no `spawn_agent` — see
> `allowed-tools`), so:claims-drafting
When your agent uses it
Draft patent claims for an invention. Use when user says "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", or wants to create patent claims. The core skill of the patent pipeline.
What it loads into context
Frontmatter
185 tokensAlways available to the agent
SKILL.md
2,833 tokensWhen the skill is activated
Reference documents
9,224 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore11,641 bytes../shared-references/patent-format-cn.mddoc9,352 bytes../shared-references/patent-format-ep.mddoc6,542 bytes../shared-references/patent-format-us.mddoc6,151 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Claims Drafting: The Core Patent Skill
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Draft patent claims based on: **$ARGUMENTS**comm-lit-review
When your agent uses it
Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
2,170 tokensWhen the skill is activated
Reference documents
1,960 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Constants
- Source Selection
- Retrieval Order
- External Search Policy
- Venue Priority
- Workflow
- Synthesis Rules
- Output
- Key Rules
Files
SKILL.mdcore9,037 bytesSKILL.mdcore9,037 bytesSKILL.mdcore9,037 bytesSKILL.mdcore9,037 bytesSKILL.mdcore9,037 bytesSKILL.mdcore9,037 bytesreferences/domain-taxonomy.mddoc1,479 bytesreferences/output-template.mddoc983 bytesreferences/source-policy.mddoc3,116 bytesreferences/venue-tiering.mddoc3,095 bytes
Read SKILL.md
# Comm Lit Review Claude Single
Research topic: $ARGUMENTS
## Purpose
Use this skill for communications-domain literature review when the topic is about:
- wireless communications
- cellular systems, `4G/5G/6G`, `NR`, `NTN`
- satellite, `LEO`, `GEO`, integrated space-air-ground systems
- Wi-Fi, WLAN, mesh, ad hoc, sidelink, V2X
- routing, scheduling, resource allocation, beamforming
- rate adaptation, link adaptation, `ACM`, `HARQ`, `CSI` feedbackdeepxiv
When your agent uses it
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,713 tokensWhen the skill is activated
Reference documents
5,148 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../../tools/deepxiv_fetch.py
Files
SKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/deepxiv_fetch.pyruns6,222 bytes
Read SKILL.md
# DeepXiv Paper Search & Progressive Reading
Search topic or paper ID: $ARGUMENTS
## Role & Positioning
DeepXiv is the progressive-reading literature source:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Batch search, PDF download, metadata |
| **`/deepxiv`** | **DeepXiv SDK** | **Progressive section-level reading** |
| `/semantic-scholar` | S2 API | Published venue metadata, citation counts |
| `/alphaxiv` | www.alphaxiv.org | Instant LLM-optimized summary of one paper, with LaTeX source fallback |dse-loop
When your agent uses it
Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
3,440 tokensWhen the skill is activated
Reference documents
4,781 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Safety Rules — READ FIRST
- Constants (override via $ARGUMENTS)
- Typical Use Cases
- Workflow
- State Recovery
- Key Rules
- Example Invocations
Files
SKILL.mdcore13,588 bytesSKILL.mdcore13,588 bytesSKILL.mdcore13,588 bytesSKILL.mdcore13,588 bytesSKILL.mdcore13,588 bytes../shared-references/external-cadence.mddoc20,174 bytes
Read SKILL.md
# DSE Loop: Autonomous Design Space Exploration
Autonomously explore a design space: run → analyze → pick next parameters → repeat, until the objective is met or timeout is reached. Designed for computer architecture and EDA problems.
## Context: $ARGUMENTS
## Safety Rules — READ FIRST
**NEVER do any of the following:**
- `sudo` anything
- `rm -rf`, `rm -r`, or any recursive deletion
- `rm` any file you did not create in this session
- Overwrite existing source files without reading them first
- `git push`, `git reset --hard`, or any destructive git operationembodiment-description
When your agent uses it
Write detailed embodiment descriptions for patent specifications. Use when user says "撰写实施例", "write embodiment", "实施例描述", "detailed description", or wants to describe how to practice an invention.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,500 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Workflow
- Key Rules
Files
SKILL.mdcore6,732 bytesSKILL.mdcore6,732 bytesSKILL.mdcore6,732 bytes
Read SKILL.md
# Embodiment Description
Write detailed embodiments for: **$ARGUMENTS**
Embodiments describe HOW to make and use the invention -- they are the patent equivalent of experiment sections, but describe the invention rather than evaluating it empirically.
## Constants
- `MIN_EMBODIMENTS = 1` — At least one complete embodiment required
- `MAX_EMBODIMENTS = 3` — Practical limit; more embodiments strengthen enablement
- `EMBODIMENT_STYLE = detailed` — `detailed` (full working example) or `outline` (sketch)
- `REFERENCE_NUMERAL_PREFIX = 100` — Starting reference numeral for first figure's components
## Inputsexa-search
When your agent uses it
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,205 tokensWhen the skill is activated
Reference documents
5,148 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../../tools/exa_search.py../../../tools/research_wiki.py
Files
SKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytesSKILL.mdcore7,961 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/exa_search.pyruns14,437 bytes../../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Exa AI-Powered Web Search
Search query: $ARGUMENTS
## Role & Positioning
Exa is the **broad web search** source with built-in content extraction:
| Skill | Best for |
|------|----------|
| `/arxiv` | Direct preprint search and PDF download |
| `/semantic-scholar` | Published venue papers (IEEE, ACM, Springer), citation counts |
| `/deepxiv` | Layered reading: search, brief, section map, section reads |
| `/exa-search` | Broad web search: blogs, docs, news, companies, research papers — with content extraction |experiment-audit
When your agent uses it
Audit experiment integrity before claiming results. Uses fresh-agent GPT-6-Astra review (same-family provisional in the base Codex mirror) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
What it loads into context
Frontmatter
207 tokensAlways available to the agent
SKILL.md
2,970 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- Core Principle
- Constants
- Workflow
- Integration with Other Skills
- Key Rules
- Acknowledgements
- Review Tracing
Files
SKILL.mdcore12,226 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Experiment Audit: Fresh-Agent Integrity Verification
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Codex assurance:** base semantic audit results recordexperiment-bridge
When your agent uses it
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
4,115 tokensWhen the skill is activated
Reference documents
9,254 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Inputs
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore17,645 bytesSKILL.mdcore17,645 bytesSKILL.mdcore17,645 bytes../shared-references/external-cadence.mddoc20,174 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Workflow 1.5: Experiment Bridge
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Implement and deploy experiments from plan: **$ARGUMENTS**experiment-plan
When your agent uses it
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
2,187 tokensWhen the skill is activated
Reference documents
2,297 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore9,665 bytes
Read SKILL.md
# Experiment Plan: Claim-Driven, Paper-Oriented Validation
Refine and concretize: **$ARGUMENTS**
## Overview
Use this skill after the method is stable enough that the next question becomes: **what exact experiments should we run, in what order, to defend the paper?** If the user wants the full chain in one request, prefer `/research-refine-pipeline`.
The goal is not to generate a giant benchmark wishlist. The goal is to turn a proposal into a **claim -> evidence -> run order** roadmap that supports four things:
1. the method actually solves the anchored problem
2. the dominant contribution is real and focused
3. the method is elegant enough that extra complexity is unnecessary
4. any frontier-model-era component is genuinely useful, not decorativeexperiment-queue
When your agent uses it
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
4,409 tokensWhen the skill is activated
Reference documents
7,427 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Why This Exists
- Core Concepts
- Workflow
- Grid Spec Syntax
- Wave Chaining
- OOM Handling
- Stale Screen Detection
- Resume-on-restart
- Output: Summary Report
- Comparison with `/run-experiment`
- Key Rules
- Known Failure Modes
- Example Session
- See Also
- Rationale / Source
Scripts executed separately
../../../tools/experiment_queue/build_manifest.py../../../tools/experiment_queue/queue_manager.py
Files
SKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytesSKILL.mdcore16,375 bytes../shared-references/compute-env-contract.mddoc10,577 bytes../shared-references/external-cadence.mddoc20,174 bytes../../../tools/experiment_queue/build_manifest.pyruns1,542 bytes../../../tools/experiment_queue/queue_manager.pyruns1,574 bytes
Read SKILL.md
# Experiment Queue
Orchestrate large batches of ML experiments on SSH remote GPU servers with proper state tracking, OOM retry, stale cleanup, and wave transitions.
## When to Use This Skill
Use when `/run-experiment` is insufficient:
- **≥10 jobs** that need batching across GPUs
- **Multi-seed sweeps** (e.g., 21 seeds × 12 cells)
- **Wave transitions** (run wave 1, wait, run wave 2, wait, run wave 3...)
- **Teacher+student chains** (train teacher then distill; auto-trigger student after teacher done)
- **OOM-prone configs** where you need to retry with different GPU or wait
- **Mixed seed grids** where failed cells need re-running
feishu-notify
When your agent uses it
Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
1,575 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Configuration
- Workflow
- Helper Function (for other skills)
- Event Catalog
- Key Rules
Files
SKILL.mdcore6,087 bytesSKILL.mdcore6,087 bytesSKILL.mdcore6,087 bytesSKILL.mdcore6,087 bytesSKILL.mdcore6,087 bytes
Read SKILL.md
# Feishu/Lark Notification
Send a notification: **$ARGUMENTS**
## Overview
This skill provides Feishu/Lark integration for ARIS. It is designed as an **internal utility** — other skills call it at key events (experiment done, review scored, checkpoint waiting). It can also be invoked manually.
**Zero-impact guarantee**: If no `feishu.json` config exists, this skill does nothing and returns silently. All existing workflows are completely unaffected.
## Configuration
The skill reads `~/.codex/feishu.json`. If this file does not exist, **all Feishu functionality is disabled** — skills behave exactly as before.
figure-description
When your agent uses it
Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with reference numerals.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,239 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Workflow
- Key Rules
Files
SKILL.mdcore5,000 bytes
Read SKILL.md
# Figure Description for Patents
Process patent figures and generate drawing descriptions based on: **$ARGUMENTS**
Unlike `/paper-figure` which generates data plots, this skill processes user-provided technical diagrams and assigns reference numerals.
## Constants
- `FIGURE_DIR = "patent/figures/"` — Output directory for figure descriptions
- `REFERENCE_NUMERAL_PREFIX = 100` — Starting numeral for first figure's components
- `NUMERAL_SERIES = 100` — Each figure uses a separate 100-series (Fig 1: 100-199, Fig 2: 200-299, etc.)
## Inputs
figure-spec
When your agent uses it
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
What it loads into context
Frontmatter
200 tokensAlways available to the agent
SKILL.md
3,214 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Core Properties
- Tool Location
- Workflow
- Schema Quick Reference
- Design Patterns
- Anti-Patterns
- Output Contract
- Integration with Other Skills
- Review Tracing
Scripts executed separately
../../../tools/figure_renderer.py
Files
SKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytesSKILL.mdcore12,057 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../../tools/figure_renderer.pyruns2,582 bytes
Read SKILL.md
# FigureSpec: Deterministic JSON → SVG Figure Generation
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate publication-quality **architecture diagrams**, **workflow pipelines**, **audit cascades**, and **system topology** figures as editable SVG vector graphics using a deterministic JSON → SVG renderer.firecrawl-search
When your agent uses it
Web search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search".
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
3,139 tokensWhen the skill is activated
Reference documents
8,355 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../../tools/firecrawl_search.py../../../tools/research_wiki.py
Files
SKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytesSKILL.mdcore11,168 bytes../shared-references/citation-discipline.mddoc13,918 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/firecrawl_search.pyruns15,149 bytes../../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Firecrawl Web Search and Scrape
Search query or URL: $ARGUMENTS
## Role & Positioning
Firecrawl is a **broad web search** source that returns the full page as markdown, plus a scraper for URLs you already have:
| Skill | Best for |
|------|----------|
| `/arxiv` | Direct preprint search and PDF download |
| `/semantic-scholar` | Published venue papers (IEEE, ACM, Springer), citation counts |
| `/openalex` | Open citation graph, affiliations, funding metadata |
| `/deepxiv` | Layered reading: search, brief, section map, section reads |formula-derivation
When your agent uses it
Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
2,057 tokensWhen the skill is activated
Reference documents
4,308 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Context: $ARGUMENTS
- Goal
- Inputs
- Workflow
- Required File Structure
- Output Modes
- Relationship to `proof-writer`
- Chat Response
- Key Rules
Files
SKILL.mdcore9,527 bytes../lean-formalize/SKILL.mddoc22,343 bytes
Read SKILL.md
# Formula Derivation: Research Theory Line Construction
Build an honest derivation package, not a fake polished theorem story.
## Constants
- DEFAULT_DERIVATION_DOC = `DERIVATION_PACKAGE.md` in project root
- STATUS = `COHERENT AS STATED | COHERENT AFTER REFRAMING / EXTRA ASSUMPTION | NOT YET COHERENT`
## Context: $ARGUMENTS
## Goal
Produce exactly one of:gemini-search
When your agent uses it
Search research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literature discovery beyond arXiv/Semantic Scholar indexes.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
2,354 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Environment & Setup
- Workflow
- Key Rules
Files
SKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytesSKILL.mdcore8,978 bytes
Read SKILL.md
# Gemini Literature Search
Search query: $ARGUMENTS
## Role & Positioning
This skill uses Gemini as a **broad literature discovery** source:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |
| `/semantic-scholar` | Semantic Scholar API | Published venue papers (IEEE, ACM, Springer) with citation counts |
| `/deepxiv` | DeepXiv CLI | Layered reading: search, brief, section map, section reads |
| `/exa-search` | Exa API | Broad web search: blogs, docs, news, companies, research papers |grant-proposal
When your agent uses it
Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
7,665 tokensWhen the skill is activated
Reference documents
4,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Grant Type Specifications
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Parameter Pass-Through
- Composing with Other Skills
- Output Protocols
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore31,592 bytesSKILL.mdcore31,592 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Grant Proposal: From Research Ideas to Fundable Application
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Draft a grant proposal based on: **$ARGUMENTS**idea-creator
When your agent uses it
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
6,168 tokensWhen the skill is activated
Reference documents
16,167 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Workflow
- Phase 7: Write Ideas to Research Wiki (if active)
- Output Protocols
- Key Rules
- Composing with Other Skills
- Review Tracing
Scripts executed separately
../../../tools/research_wiki.py../../../tools/threat_scan.py
Files
SKILL.mdcore25,599 bytesSKILL.mdcore25,599 bytesSKILL.mdcore25,599 bytesSKILL.mdcore25,599 bytesSKILL.mdcore25,599 bytesSKILL.mdcore25,599 bytes../shared-references/fan-out-pattern.mddoc23,134 bytes../shared-references/injection-hygiene.mddoc8,044 bytes../shared-references/output-composition.mddoc5,293 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc1,753 bytes../shared-references/output-versioning.mddoc4,828 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/wiki-helper-resolution.mddoc2,933 bytes../../../tools/research_wiki.pyruns78,927 bytes../../../tools/threat_scan.pyruns12,166 bytes
Read SKILL.md
# Research Idea Creator
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate publishable research ideas for: $ARGUMENTSidea-discovery
When your agent uses it
Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
5,523 tokensWhen the skill is activated
Reference documents
5,698 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Checkpoint execution rule
- Per-stage evidence gate (`RESUMABLE = true`)
- Pipeline
- Output Protocols
- Render HTML view (auto, when `RENDER_HTML = true`)
- Key Rules
- Composing with Workflow 2
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore22,951 bytesSKILL.mdcore22,951 bytesSKILL.mdcore22,951 bytesSKILL.mdcore22,951 bytes../shared-references/output-composition.mddoc5,293 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Workflow 1: Idea Discovery Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Orchestrate a complete idea discovery workflow for: **$ARGUMENTS**idea-discovery-robot
When your agent uses it
Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says \"robotics idea discovery\", \"机器人找idea\", \"embodied AI idea\", \"机器人方向探索\", \"sim2real 选题\", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
3,538 tokensWhen the skill is activated
Reference documents
4,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Execution Rule
- Phase 0: Frame the Robotics Problem
- Phase 1: Robotics Literature Survey
- Phase 2: Robotics-Specific Idea Generation and Filtering
- Phase 3: Feasibility and Pilot Design
- Phase 4: Deep Novelty Verification
- Phase 5: External Robotics Review
- Phase 6: Final Report
- Key Rules
- Composing with Later Work
- Output Protocols
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore15,898 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Robotics Idea Discovery Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Orchestrate a robotics-specific idea discovery workflow for: **$ARGUMENTS**integrity-forensics
When your agent uses it
Run the Anti-Autoresearch integrity-forensics DETERMINISTIC slice (numeric core + rules-only reporter) against a paper via a SHA-pinned thin launcher, then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Codex-native limitation: upstream ships no Codex-native auditor pack, so the full nine-dimension semantic sweep requires a Claude Code session — this pack runs the honestly-scoped deterministic-only mode (it can flag, it can never say CLEAN). Use when user says "integrity forensics", "forensic audit this paper", "投稿前自查诚信".
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
1,629 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Step 0 — Bootstrap the pin (identical to mainline)
- Step 1 — Delegate: upstream deterministic-only mode, unchanged
- Step 2 — Typed gate + obligations
- Step 3 — Fix what it found
Files
SKILL.mdcore6,184 bytesSKILL.mdcore6,184 bytesSKILL.mdcore6,184 bytesSKILL.mdcore6,184 bytesSKILL.mdcore6,184 bytesSKILL.mdcore6,184 bytes
Read SKILL.md
# Integrity Forensics — thin launcher (Codex-native: deterministic slice)
Audit target: **$ARGUMENTS**
> Same launcher doctrine as the mainline skill: SHA-pin, upstream eval-gate
> validation per pin, delegate unchanged, no vendoring, no forking, **no
> reviewer knobs**. The one Codex-native difference: upstream's nine auditor
> skills are Claude-Code contracts, so this pack runs upstream's
> **deterministic-only mode** — the numeric forensic core (GRIM / GRIMMER /
> statcheck / delta arithmetic) plus the rules-only reporter with an
> all-`review_unavailable` coverage map. That mode is honestly scoped by
> upstream: it can raise HARD/SOFT flags; it can NEVER return
> `CLEAN_GIVEN_EVIDENCE`. Translating upstream's reviewer calls into
> `spawn_agent` would REWRITE an upstream contract — forbidden.interview-cheatsheet
When your agent uses it
Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.
What it loads into context
Frontmatter
264 tokensAlways available to the agent
SKILL.md
3,818 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- Style guide — STRICT (read `docs/tutorials/attention_tutorial.md` as canonical reference)
- Workflow
- Update the index
- Key invariants (the ARIS rules baked in)
- When NOT to use
- Reference invocations
- Reference style files
- Provenance
Files
SKILL.mdcore14,557 bytesSKILL.mdcore14,557 bytesSKILL.mdcore14,557 bytesSKILL.mdcore14,557 bytesSKILL.mdcore14,557 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# /interview-cheatsheet — long-form Chinese ML/LLM interview prep
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate one comprehensive Chinese cheat sheet per invocation: formulas + derivations + from-scratch code + 25 高频题. Output receives a fresh selected math/code review before rendering; same-family positives remain provisional. **Detect-only by default: never auto-commits.**invention-structuring
When your agent uses it
Structure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
1,721 tokensWhen the skill is activated
Reference documents
4,128 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore7,909 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Invention Structuring
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Structure the invention into a formal disclosure based on: **$ARGUMENTS**jurisdiction-format
When your agent uses it
Compile patent application into jurisdiction-specific filing format. Use when user says "格式转换", "jurisdiction format", "国家格式", "compile patent", or wants formatted patent documents for CN/US/EP filing.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,689 tokensWhen the skill is activated
Reference documents
5,096 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore6,816 bytes../shared-references/patent-format-cn.mddoc9,352 bytes../shared-references/patent-format-ep.mddoc6,542 bytes../shared-references/patent-format-us.mddoc6,151 bytes
Read SKILL.md
# Jurisdiction Format: Patent Filing Compilation
Compile the patent application into filing-ready format based on: **$ARGUMENTS**
Analogous to `/paper-compile` but for patent document formatting instead of LaTeX.
## Constants
- `JURISDICTION = "auto"` — From pipeline or args: `CN`, `US`, `EP`, `ALL`
- `PATENT_TYPE = "invention"` — `invention` (发明专利) or `utility_model` (实用新型, CN only)
- `OUTPUT_FORMAT = "markdown"` — `markdown` (for review) or `docx` (for filing, requires python-docx)
- `OUTPUT_DIR = "patent/output/"` — Base output directory
## Inputskeenable-search
When your agent uses it
Keyless web search and page fetch via Keenable. Use when user says "keenable search", "web search without an API key", "fetch this page as markdown", or needs broad web results beyond academic databases (arXiv, Semantic Scholar) with no search API key set up.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,809 tokensWhen the skill is activated
Reference documents
5,148 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
Scripts executed separately
../../../tools/keenable_search.py
Files
SKILL.mdcore6,559 bytesSKILL.mdcore6,559 bytesSKILL.mdcore6,559 bytesSKILL.mdcore6,559 bytesSKILL.mdcore6,559 bytesSKILL.mdcore6,559 bytesSKILL.mdcore6,559 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/keenable_search.pyruns11,367 bytes
Read SKILL.md
# Keenable Web Search
Search query: $ARGUMENTS
## Role & Positioning
Keenable is a **broad web search** source that works without an API key or extra Python packages:
| Skill | Best for |
|------|----------|
| `/arxiv` | Direct preprint search and PDF download |
| `/semantic-scholar` | Published venue papers (IEEE, ACM, Springer), citation counts |
| `/exa-search` | Broad web search with content extraction (highlights, summaries); needs `EXA_API_KEY` |
| `/keenable-search` | Broad web search with a page-text snippet per result, plus fetching a known URL as markdown; no key needed |kill-argument
When your agent uses it
Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.
What it loads into context
Frontmatter
214 tokensAlways available to the agent
SKILL.md
5,679 tokensWhen the skill is activated
Reference documents
7,559 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- How This Differs From Other Review Skills
- When To Use
- Constants
- Workflow
- Output Contract
- Key Rules
- When NOT to Use
- Review Tracing
- Notes
Files
SKILL.mdcore23,623 bytesSKILL.mdcore23,623 bytesSKILL.mdcore23,623 bytesSKILL.mdcore23,623 bytesSKILL.mdcore23,623 bytesSKILL.mdcore23,623 bytesSKILL.mdcore23,623 bytesSKILL.mdcore23,623 bytes../shared-references/fan-out-pattern.mddoc23,134 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Kill Argument Exercise: Adversarial Attack-Defense Review
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Review assurance:** with the default native Codex reviewers, recordlean-formalize
When your agent uses it
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific proof obligation benefits from formal verification; use proof-writer for ordinary mathematical drafting.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
4,308 tokensWhen the skill is activated
Reference documents
15,746 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use Lean
- Core workflow
- Scope and entry
- 1. Fix meaning before implementation
- 2. Design the connections, then build useful pieces
- 3. Use computation with a proved interpretation
- 4. Review the mathematical obligations that remain uncertain
- 5. Verify the actual final target
- 6. Persist and hand off the evidence actually obtained
Files
SKILL.mdcore22,343 bytesSKILL.mdcore22,343 bytesSKILL.mdcore22,343 bytesSKILL.mdcore22,343 bytesSKILL.mdcore22,343 bytesagents/openai.yamlasset261 bytesreferences/adversarial-review.mddoc14,165 bytesreferences/lean-working-loop.mddoc10,625 bytesreferences/verification-and-handoff.mddoc6,332 bytes../shared-references/fan-out-pattern.mddoc23,134 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-routing.mddoc8,348 bytes
Read SKILL.md
# Lean Formalize
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Turn the user's mathematical statement into a checked Lean theorem with itsmermaid-diagram
When your agent uses it
Generate Mermaid diagrams from user requirements. Save .mmd and .md files to figures/ with syntax verification. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and many more diagram types.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
2,962 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Workflow: MUST EXECUTE ALL STEPS
- Architecture Diagram Best Practices
- CVPR/ICLR/NeurIPS Style Guide (for Academic Diagrams)
- Math Formulas in Diagrams (KaTeX)
- Code Quality Rules
- Output Structure
- Key Rules (MUST FOLLOW)
Files
SKILL.mdcore12,163 bytesSKILL.mdcore12,163 bytesSKILL.mdcore12,163 bytesSKILL.mdcore12,163 bytesSKILL.mdcore12,163 bytesSKILL.mdcore12,163 bytesSKILL.mdcore12,163 bytesSKILL.mdcore12,163 bytes
Read SKILL.md
# Mermaid Diagram Generator
Generate high-quality Mermaid diagram code based on user requirements, with file output and verification.
## Constants
- **OUTPUT_DIR = `figures/`** — Output directory for generated files
- **MAX_ITERATIONS = 3** — Maximum refinement rounds for syntax or layout issues
## Workflow: MUST EXECUTE ALL STEPS
### Step 0: Pre-flight Check
# Create output directorymeta-apply
When your agent uses it
Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved, with a fresh landing review and human approval. Base Codex review is same-family provisional. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
2,385 tokensWhen the skill is activated
Reference documents
12,067 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The acquittal is generated HERE, not relayed
- The non-negotiable rules (jury-at-landing, reject-default)
- Workflow
- Provenance is a receipt, not an acquittal of correctness
- Key Rules
- Review Tracing
Scripts executed separately
../../../tools/provenance.py
Files
SKILL.mdcore9,561 bytesSKILL.mdcore9,561 bytesSKILL.mdcore9,561 bytesSKILL.mdcore9,561 bytes../meta-optimize/SKILL.mddoc18,401 bytes../shared-references/review-scope-limits.mddoc4,174 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc1,809 bytes../shared-references/skill-governance.mddoc7,344 bytes../../../tools/provenance.pyruns13,754 bytes
Read SKILL.md
# Meta-Apply: the privileged landing gate for self-modification patches
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Review assurance:** a same-family landing review uses `stamp-provisional`meta-optimize
When your agent uses it
Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.
What it loads into context
Frontmatter
207 tokensAlways available to the agent
SKILL.md
4,383 tokensWhen the skill is activated
Reference documents
5,581 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- What This Skill Optimizes (Harness Components)
- Prerequisites
- Workflow
- Key Rules
- Event Schema Reference
- Triggering
- Acknowledgements
- Output Protocols
- Review Tracing
Scripts executed separately
../../../tools/capture_filter.py../../../tools/meta_opt/trigger_eval.py
Files
SKILL.mdcore18,401 bytesSKILL.mdcore18,401 bytesSKILL.mdcore18,401 bytesSKILL.mdcore18,401 bytes../shared-references/capture-antipatterns.mddoc5,259 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc1,753 bytes../shared-references/output-versioning.mddoc4,828 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../../tools/capture_filter.pyruns6,080 bytes../../../tools/meta_opt/trigger_eval.pyruns13,384 bytes
Read SKILL.md
# Meta-Optimize: Outer-Loop Harness Optimization for ARIS
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Analyze accumulated usage logs and propose optimizations for: **$ARGUMENTS**monitor-experiment
When your agent uses it
Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
828 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Rules
Files
SKILL.mdcore3,378 bytesSKILL.mdcore3,378 bytesSKILL.mdcore3,378 bytesSKILL.mdcore3,378 bytesSKILL.mdcore3,378 bytesSKILL.mdcore3,378 bytesSKILL.mdcore3,378 bytesSKILL.mdcore3,378 bytes
Read SKILL.md
# Monitor Experiment Results
Monitor: $ARGUMENTS
## Workflow
### Step 1: Check What's Running
First identify the backend from `AGENTS.md`, run notes, or launch summary: local, SSH, Vast.ai, or Modal. Monitor the backend that was actually used; do not assume a plain SSH screen session when the run was launched through Vast.ai or Modal.
```bash
ssh <server> "screen -ls"
```
novelty-check
When your agent uses it
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,639 tokensWhen the skill is activated
Reference documents
4,537 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Instructions
- Review Tracing
Files
SKILL.mdcore6,817 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Novelty Check Skill
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Check whether a proposed method/idea has already been done in the literature: **$ARGUMENTS**openalex
When your agent uses it
Search academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
2,676 tokensWhen the skill is activated
Reference documents
5,148 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Setup
- Workflow
- Key Rules
- OpenAlex vs Other Sources
Scripts executed separately
../../../tools/openalex_fetch.py
Files
SKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytesSKILL.mdcore9,998 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/openalex_fetch.pyruns12,106 bytes
Read SKILL.md
# OpenAlex Academic Search
Search query: $ARGUMENTS
## Role & Positioning
This skill uses OpenAlex as a **comprehensive open academic graph** source:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |
| `/semantic-scholar` | Semantic Scholar API | Published venue papers (IEEE, ACM, Springer) with citation counts |
| `/openalex` | OpenAlex API | **Open citation graph, institutional affiliations, funding data, comprehensive metadata** |
| `/deepxiv` | DeepXiv CLI | Layered reading: search, brief, section map, section reads |overleaf-sync
When your agent uses it
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to bridge their ARIS paper directory with an Overleaf project.
What it loads into context
Frontmatter
135 tokensAlways available to the agent
SKILL.md
2,840 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Constants
- Architecture
- Sub-commands
- Conflict Resolution
- Token Security — Defense in Depth
- Mutual-Exclusion Rule
- Output Contract
- See Also
Scripts executed separately
../../../tools/overleaf_audit.sh../../../tools/overleaf_setup.sh
Files
SKILL.mdcore11,115 bytesSKILL.mdcore11,115 bytesSKILL.mdcore11,115 bytesSKILL.mdcore11,115 bytesSKILL.mdcore11,115 bytesSKILL.mdcore11,115 bytesSKILL.mdcore11,115 bytesSKILL.mdcore11,115 bytes../../../tools/overleaf_audit.shruns3,516 bytes../../../tools/overleaf_setup.shruns6,412 bytes
Read SKILL.md
# Overleaf Sync
Bridge a local paper directory with an Overleaf project so that:
- **You** can keep editing in the Overleaf web UI (or share editing access with collaborators)
- **ARIS** can read your changes, run audits (`/paper-claim-audit`, `/citation-audit`, `/auto-paper-improvement-loop`), and push fixes back
This uses the official **Overleaf Git bridge** (Premium feature). The agent **never sees your authentication token** — you do the one-time auth manually so the token lives in macOS Keychain, not in chat history or `.git/config`.
## When to Use This Skill
- You want to use Overleaf as the editing surface (better collaboration, shared with team) but still run ARIS pipelines locally
- You want to take an existing local ARIS paper and push it to Overleaf for a co-author to edit
- A collaborator made changes in Overleaf and you want to pull + diff them before continuing local workpaper-claim-audit
When your agent uses it
Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh Codex reviewer with no prior context; base output is same-family provisional. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
What it loads into context
Frontmatter
203 tokensAlways available to the agent
SKILL.md
3,762 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- How This Differs From Other Audit Skills
- Core Principle
- Workflow
- When to Run
- Integration with Other Skills
- Render HTML view (auto, when `RENDER_HTML = true`, default)
- Key Rules
- Review Tracing
- Submission Artifact Emission
Files
SKILL.mdcore15,164 bytesSKILL.mdcore15,164 bytesSKILL.mdcore15,164 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Paper Claim Audit: Zero-Context Evidence Verification
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Codex assurance:** write `review_independence: same-family` andpaper-compile
When your agent uses it
Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-ready PDF.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
2,528 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Workflow
- Key Rules
- Common Venue Requirements
Files
SKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytesSKILL.mdcore9,381 bytes
Read SKILL.md
# Paper Compile: LaTeX to Submission-Ready PDF
Compile the LaTeX paper and fix any issues: **$ARGUMENTS**
## Constants
- **COMPILER = `latexmk`** — LaTeX build tool. Handles multi-pass compilation automatically.
- **ENGINE = `pdflatex`** — LaTeX engine. Options: `pdflatex` (default), `xelatex` (for CJK/custom fonts), `lualatex`.
- **MAX_COMPILE_ATTEMPTS = 3** — Maximum attempts to fix errors and recompile.
- **PAPER_DIR = `paper/`** — Directory containing LaTeX source files.
- **MAX_PAGES** — Page limit. ML conferences: main body to Conclusion end (excluding references & appendix). ICLR=9, NeurIPS=9, ICML=8. **IEEE venues: references ARE included in page count.** IEEE journal ≈ 12-14 pages, IEEE conference ≈ 5-8 pages (all inclusive).
- **RESCUE_ON_REPEAT_FAILURE = true** — If the same compile class fails after two attempts, preserve `compile.log` and ask for a focused rescue / second opinion before further edits.
## Workflowpaper-figure
When your agent uses it
Generate publication-quality figures and tables from experiment results. Use when user says \"画图\", \"作图\", \"generate figures\", \"paper figures\", or needs plots for a paper.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
3,715 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope: What This Skill Can and Cannot Do
- Constants
- Inputs
- Workflow
- Output
- Key Rules
- Figure Type Reference
- Acknowledgements
Files
SKILL.mdcore14,383 bytesSKILL.mdcore14,383 bytesSKILL.mdcore14,383 bytesSKILL.mdcore14,383 bytesSKILL.mdcore14,383 bytesSKILL.mdcore14,383 bytesSKILL.mdcore14,383 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Paper Figure: Publication-Quality Plots from Experiment Data
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate all figures and tables for a paper based on: **$ARGUMENTS**paper-illustration
When your agent uses it
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Codex-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
6,999 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Design Philosophy
- Constants
- CVPR/ICLR/NeurIPS Top-Tier Conference Style Guide
- Scope
- Workflow: MUST EXECUTE ALL STEPS
- Key Rules (MUST FOLLOW - STRICT)
- Output Structure
- Model Summary
Files
SKILL.mdcore30,036 bytesSKILL.mdcore30,036 bytesSKILL.mdcore30,036 bytesSKILL.mdcore30,036 bytesSKILL.mdcore30,036 bytesSKILL.mdcore30,036 bytes
Read SKILL.md
# Paper Illustration: Multi-Stage Codex-Supervised Figure Generation
Generate publication-quality illustrations using a **multi-stage workflow** with **Codex as the STRICT supervisor/reviewer**.
## Core Design Philosophy
```
┌──────────────────────────────────────────────────────────────────────────┐
│ MULTI-STAGE ITERATIVE WORKFLOW │
├──────────────────────────────────────────────────────────────────────────┤
│ │
│ User Request │
│ │ │
│ ▼ │paper-illustration-image2
When your agent uses it
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to `paper-illustration`, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.
What it loads into context
Frontmatter
225 tokensAlways available to the agent
SKILL.md
4,276 tokensWhen the skill is activated
Reference documents
7,324 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Design Philosophy
- Constants
- CVPR/ICLR/NeurIPS Top-Tier Conference Style Guide
- Scope
- Workflow: MUST EXECUTE ALL STEPS
- Step 1: Claude Plans the Figure
- Step 2: Layout Optimization
- Step 3: Style Verification
- Step 4: Generate Through the Bridge
- Step 5: Review the Output
- Step 6: Refine if Needed
- Step 7: Finalize And Verify
- Key Rules
- Repair Path
- Output Structure
- Model Summary
Scripts executed separately
scripts/paper_illustration_image2.py../../../tools/paper_illustration_image2.py
Files
SKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesSKILL.mdcore19,813 bytesscripts/paper_illustration_image2.pyruns8,745 bytes../shared-references/integration-contract.mddoc19,930 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../../tools/paper_illustration_image2.pyruns2,205 bytes
Read SKILL.md
# Paper Illustration Image2
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate publication-quality paper figures using **Claude as the planner/reviewer**paper-plan
When your agent uses it
Generate a structured paper outline from review conclusions and experiment results. Use when user says \"写大纲\", \"paper outline\", \"plan the paper\", \"论文规划\", or wants to create a paper plan before writing.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
3,374 tokensWhen the skill is activated
Reference documents
8,817 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Orchestra-Guided Writing Overlay
- Workflow
- Key Rules
- Acknowledgements
- Output Protocols
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore13,694 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/venue-checklists.mddoc2,939 bytes../shared-references/writing-principles.mddoc17,539 bytes
Read SKILL.md
# Paper Plan: From Review Conclusions to Paper Outline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
paper-poster
When your agent uses it
DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
197 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore841 bytesSKILL.mdcore841 bytes
Read SKILL.md
# Paper Poster (DEPRECATED → /paper-poster-html)
This skill is retired. The LaTeX/tcbposter pipeline it described produced posters with
unbounded color palettes, no real paper figures, and no print-canvas verification, and
has been replaced by the measurement-gated HTML/CSS pipeline.
**Immediately proceed with `/paper-poster-html`**, passing through all of the user's
arguments unchanged. Do not attempt the legacy LaTeX flow.
The full legacy implementation remains available in git history
(`git log -- skills/skills-codex/paper-poster/SKILL.md`) if a venue ever mandates
LaTeX poster source — none is known to.paper-poster-html
When your agent uses it
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster.
What it loads into context
Frontmatter
242 tokensAlways available to the agent
SKILL.md
5,588 tokensWhen the skill is activated
Reference documents
5,663 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this skill exists (the failure it prevents)
- Mental model
- Constants
- Workflow
- State persistence
- Key rules
- Review tracing
- Output contract
- When NOT to use
Files
SKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytesSKILL.mdcore22,113 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/taste-calibration.mddoc4,819 bytes
Read SKILL.md
# Paper Poster (HTML): measurement-gated poster generation
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
One HTML file styled for an exact print canvas (`@page { size: W H }`), rendered to PDFpaper-slides
When your agent uses it
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
What it loads into context
Frontmatter
207 tokensAlways available to the agent
SKILL.md
5,691 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Constants
- Talk Type → Slide Count
- Venue Color Schemes
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Parameter Pass-Through
Files
SKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytesSKILL.mdcore20,320 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Paper Slides: From Paper to Conference Talk
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Generate conference presentation slides from: **$ARGUMENTS**paper-talk
When your agent uses it
End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline", "end-to-end slides", "做演讲", "conference talk full workflow". Use when the user wants the complete talk artifact, not just a slide deck.
What it loads into context
Frontmatter
224 tokensAlways available to the agent
SKILL.md
5,422 tokensWhen the skill is activated
Reference documents
6,258 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Assurance Ladder
- Hard Invariants
- Constants
- Inputs
- Output Layout
- Workflow
- Effort Levels
- Parameter Pass-Through
- When NOT to Use
- Prior Skill Relationship
- Empirical Origin
Files
SKILL.mdcore21,740 bytesSKILL.mdcore21,740 bytesSKILL.mdcore21,740 bytesSKILL.mdcore21,740 bytesSKILL.mdcore21,740 bytesSKILL.mdcore21,740 bytes../shared-references/assurance-contract.mddoc7,707 bytes../shared-references/effort-contract.mddoc5,999 bytes../shared-references/experiment-integrity.mddoc2,355 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Paper Talk: End-to-End Conference Talk Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Workflow: from a completed paper to a conference-ready talk artifact —paper-write
When your agent uses it
Draft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTeX content from a paper plan.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
6,790 tokensWhen the skill is activated
Reference documents
9,727 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Orchestra-Guided Writing Overlay
- Templates
- Workflow
- Key Rules
- Writing Quality Reference
- Acknowledgements
Files
SKILL.mdcore28,550 bytesSKILL.mdcore28,550 bytesSKILL.mdcore28,550 bytesSKILL.mdcore28,550 bytesSKILL.mdcore28,550 bytesSKILL.mdcore28,550 bytesSKILL.mdcore28,550 bytestemplates/IEEEtran.bstasset57,748 bytestemplates/IEEEtran.clsasset281,957 bytestemplates/aaai2026.bstasset30,207 bytestemplates/aaai2026.styasset11,802 bytestemplates/aaai2026.texasset63,140 bytestemplates/acl.styasset11,615 bytestemplates/acl2026.texasset14,533 bytestemplates/acl_natbib.bstasset45,186 bytestemplates/acm.bstasset90,333 bytestemplates/acm_mm2026.texasset5,802 bytestemplates/acmart.clsasset116,554 bytestemplates/cvpr.bstasset26,900 bytestemplates/cvpr.styasset17,969 bytestemplates/cvpr2026.texasset2,116 bytestemplates/iclr2026.texasset1,924 bytestemplates/iclr2026_conference.bstasset26,973 bytestemplates/iclr2026_conference.styasset9,025 bytestemplates/icml2026.styasset27,344 bytestemplates/icml2026.texasset29,714 bytestemplates/ieee_conference.texasset2,124 bytestemplates/ieee_journal.texasset2,557 bytestemplates/math_commands.texasset1,279 bytestemplates/neurips2026.texasset19,076 bytestemplates/neurips_2026.styasset13,462 bytes../shared-references/citation-discipline.mddoc13,918 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/venue-checklists.mddoc2,939 bytes../shared-references/writing-principles.mddoc17,539 bytes
Read SKILL.md
# Paper Write: Section-by-Section LaTeX Generation
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
paper-writing
When your agent uses it
Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
9,529 tokensWhen the skill is activated
Reference documents
14,230 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Inputs
- Pipeline
- Output Protocols
- Key Rules
- Composing with Other Workflows
- Typical Timeline
Scripts executed separately
../../../tools/verify_paper_audits.sh
Files
SKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytesSKILL.mdcore38,073 bytes../shared-references/integration-contract.mddoc19,930 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc1,753 bytes../shared-references/output-versioning.mddoc4,828 bytes../shared-references/review-scope-limits.mddoc4,174 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/writing-principles.mddoc17,539 bytes../../../tools/verify_paper_audits.shruns21,578 bytes
Read SKILL.md
# Workflow 3: Paper Writing Pipeline
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Writer selection is separate; follow the
> writing-worker guidance below when drafting or revising prose.
patent-novelty-check
When your agent uses it
Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
1,634 tokensWhen the skill is activated
Reference documents
5,533 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore6,931 bytes../shared-references/patent-format-us.mddoc6,151 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Patent Novelty and Non-Obviousness Check
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Assess patentability of: **$ARGUMENTS**patent-pipeline
When your agent uses it
Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
3,703 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- Patent Type Specifications
- State Persistence (Compact Recovery)
- Workflow
- Key Rules
- Composing with Other Workflows
- Acknowledgements
Files
SKILL.mdcore15,268 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Patent Pipeline: From Invention to Filing
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Draft a complete patent application based on: **$ARGUMENTS**patent-review
When your agent uses it
Get an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.
What it loads into context
Frontmatter
176 tokensAlways available to the agent
SKILL.md
1,895 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Prerequisites
- Inputs
- Workflow
- Key Rules
Files
SKILL.mdcore7,785 bytesSKILL.mdcore7,785 bytesSKILL.mdcore7,785 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Patent Examiner Review via Codex MCP (xhigh reasoning)
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Get a multi-round patent examiner review of the patent application based on: **$ARGUMENTS**pixel-art
When your agent uses it
Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,653 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Design Principles
- Workflow
- Capability Rule
- Common Pitfalls
Files
SKILL.mdcore5,596 bytes
Read SKILL.md
# Pixel Art SVG Generator
Create a pixel art SVG illustration: $ARGUMENTS
## Design Principles
### Pixel Grid
- Each "pixel" is a `<rect>` with width/height of 7px
- Grid spacing: 7px (no gaps between pixels)
- Characters are typically 8-10 pixels wide, 8-12 pixels tall
- Use `<g transform="translate(x,y)">` to position and reuse character groups
### Color Palette
Keep it simple — 3-5 colors per character:prior-art-search
When your agent uses it
Search patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants to find relevant prior art.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,290 tokensWhen the skill is activated
Reference documents
1,373 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
SKILL.mdcore5,538 bytes../shared-references/prior-art-databases.mddoc5,455 bytes
Read SKILL.md
# Prior Art Search
Search patents and literature for prior art relevant to: **$ARGUMENTS**
Adapted from `/research-lit` for patent-specific searching.
## Constants
- `MAX_PATENT_RESULTS = 20` — Maximum patent documents to analyze in detail
- `MAX_PAPER_RESULTS = 15` — Maximum academic papers to analyze in detail
- `SEARCH_YEARS = 10` — How many years back to search
- `PATENT_DATABASES = "google-patents, espacenet"` — Patent databases to search
## Inputsproof-checker
When your agent uses it
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via fresh-agent Codex GPT-6-Astra ultra review, fixes each gap with full derivations, re-reviews, and generates an audit report. Base review is same-family provisional. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
8,001 tokensWhen the skill is activated
Reference documents
11,867 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- Issue Taxonomy (20 categories, 4 groups)
- Two-Axis Severity System
- Side-Condition Checklists for Common Theorems
- Workflow
- Key Rules
- Output Files
- Submission Artifact Emission
- Example Invocations
Scripts executed separately
../../../tools/research_wiki.py
Files
../lean-formalize/SKILL.mddoc22,343 bytesSKILL.mdcore32,049 bytesSKILL.mdcore32,049 bytesSKILL.mdcore32,049 bytesSKILL.mdcore32,049 bytesSKILL.mdcore32,049 bytes../shared-references/fan-out-pattern.mddoc23,134 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Proof Checker: Rigorous Mathematical Verification & Fixing
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Codex assurance:** base Codex proof judgments areproof-orchestrator
When your agent uses it
Manage a stateful, run-directory-based proof project with Codex: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
4,035 tokensWhen the skill is activated
Reference documents
10,446 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role
- Untrusted-Content Rule
- Run Directory
- Continuing a Project
- Status Labels
- Notation Gate
- Derivation Structure Gate
- Workflow
- Optional DeepSeek Audit
- Manual Handoff Contract
- GPT Pro Output Repair
- Guardrails
Files
../lean-formalize/SKILL.mddoc22,343 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesSKILL.mdcore19,099 bytesreferences/audit-output-contract.mddoc4,503 bytesreferences/deepseek-routing.mddoc3,590 bytesreferences/dispatch-prompts.mddoc7,823 bytesreferences/notation-audit.mddoc5,327 bytesreferences/proof-audit-rubric.mddoc4,430 bytesreferences/stress-tests.mddoc1,812 bytes
Read SKILL.md
# Proof Orchestrator
## Role
Run proof work as a local-first pipeline. Codex first attempts the proof, checks its correctness, and edits it for clarity and economy. Escalate the remaining hard obligation to GPT Pro.
Default escalation is manual: maintain the sources locally and give the user an exact browser-ready prompt. Invoking this skill does not authorize Codex to operate a browser, upload files, or spend API credit. An optional external `call-gpt-pro` skill may be used only when it is installed and the user explicitly asks Codex to perform the GPT Pro call for the current run.
An adversarial DeepSeek audit is an optional review mode inside this skill, not
a separate proof-checker. Run it only when the user explicitly requests
DeepSeek review or an independent second opinion for the current proof run.
Existing paper workflows continue to use ARIS's canonical `/proof-checker`;
do not replace that submission gate with this optional route.
proof-writer
When your agent uses it
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
1,812 tokensWhen the skill is activated
Reference documents
4,308 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Context: $ARGUMENTS
- Goal
- Inputs
- Workflow
- Required File Structure
- Output Modes
- Chat Response
- Key Rules
Files
../lean-formalize/SKILL.mddoc22,343 bytesSKILL.mdcore8,297 bytes
Read SKILL.md
# Proof Write: Rigorous Theorem / Lemma Drafting
Write a mathematically honest proof package, not a polished fake proof.
## Constants
- DEFAULT_PROOF_DOC = `PROOF_PACKAGE.md` in project root
- STATUS = `PROVABLE AS STATED | PROVABLE AFTER WEAKENING / EXTRA ASSUMPTION | NOT CURRENTLY JUSTIFIED`
## Context: $ARGUMENTS
## Goal
Produce exactly one of:qzcli
When your agent uses it
Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed training jobs on a Qizhi instance.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
2,315 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Environment contract
- Installation
- Configuration
- Quick Start
- Authentication
- Resource Discovery
- Check Available Nodes
- Job Submission
- Batch Submission
- Job Management
- Troubleshooting
Files
SKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytesSKILL.mdcore7,947 bytes../shared-references/compute-env-contract.mddoc10,577 bytes
Read SKILL.md
# qzcli — 启智平台任务管理
A kubectl/docker-style CLI for managing GPU compute jobs on the Qizhi (启智) platform.
**GitHub:** [tianyilt/qzcli_tool](https://github.com/tianyilt/qzcli_tool)
## Environment contract
Qizhi is the scheduler-cluster shape of `../shared-references/compute-env-contract.md`:
images are built OFF-platform and referenced at submit time, so the declarative
env spec + `env:<name>@<specHash>` ledger (`.aris/compute/qizhi.md`) is what
keeps "which image has which stack" answerable. Run the kernel witness inside a
submitted job (not on the login side) before trusting an image for a long run.
rebuttal
When your agent uses it
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
What it loads into context
Frontmatter
201 tokensAlways available to the agent
SKILL.md
4,099 tokensWhen the skill is activated
Reference documents
6,487 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope
- Lifecycle Position
- Constants
- Required Inputs
- Safety Model
- Workflow
- Key Rules
- Review Tracing
Files
SKILL.mdcore16,670 bytesSKILL.mdcore16,670 bytesSKILL.mdcore16,670 bytesSKILL.mdcore16,670 bytesSKILL.mdcore16,670 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-routing.mddoc8,348 bytes
Read SKILL.md
# Workflow 4: Rebuttal
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Prepare and maintain a grounded, venue-compliant rebuttal for: **$ARGUMENTS**render-html
When your agent uses it
Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.
What it loads into context
Frontmatter
256 tokensAlways available to the agent
SKILL.md
5,248 tokensWhen the skill is activated
Reference documents
4,126 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- Core invariants
- Tool Location
- Invocation
- Workflow
- What the helper supports
- Two-phase integration plan (Phase 1 is this skill; Phase 2 is workflow hooks)
- Customizing the templates
- External alternatives (for richer surfaces)
- Key rules
Scripts executed separately
scripts/render_html.py
Files
SKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesSKILL.mdcore21,134 bytesscripts/render_html.pyruns37,028 bytesscripts/templates/academic.htmlasset8,651 bytesscripts/templates/dashboard.htmlasset8,371 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-routing.mddoc8,348 bytes
Read SKILL.md
# /render-html: Markdown → single-file HTML for human reading
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Markdown is for writers. HTML is for readers.** ARIS workflow nodes write Markdown (canonical, audit-trail-friendly, machine-parseable). `/render-html` turns *selected* artifacts into a polished single-file HTML view for the human who actually has to read them. The Markdown stays the source of truth.research-implement-feature
When your agent uses it
Build a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BEFORE the code that depends on it and a sweep for the ones that slipped through undeclared (same-family provisional in the base Codex mirror). Use when user says "给我实现", "implement X", "帮我做一个能跑的", "先搭个原型再加功能", "build this feature", "prototype then extend", or hands over a capability description rather than an experiment plan.
What it loads into context
Frontmatter
285 tokensAlways available to the agent
SKILL.md
5,591 tokensWhen the skill is activated
Reference documents
15,571 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Two invariants
- Scope boundary
- Constants
- Interaction rule (HARD CONSTRAINT)
- Acceptance-gate provenance
- Artifacts
- The assumption ledger
- Stub discipline
- Phase 0 — Read the request, open the ledger
- Phase 1 — Build the feature ladder
- Phase 2 — F0, the spine
- Phase 3 — One rung at a time
- Phase 4 — Silent-assumption sweep (Type-B; same-family stays provisional)
- Phase 5 — Report
- Anti-patterns to refuse
- See Also
Files
SKILL.mdcore22,626 bytesSKILL.mdcore22,626 bytesSKILL.mdcore22,626 bytes../shared-references/acceptance-gate.mddoc19,333 bytes../shared-references/capture-antipatterns.mddoc5,259 bytes../shared-references/effort-contract.mddoc5,999 bytes../shared-references/injection-hygiene.mddoc8,044 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/review-scope-limits.mddoc4,174 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc1,809 bytes../shared-references/reviewer-routing.mddoc8,348 bytes
Read SKILL.md
# Research Implement: Feature — Codex-native
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Review assurance.** A same-family Phase 4 sweep recordsresearch-lit
When your agent uses it
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
7,710 tokensWhen the skill is activated
Reference documents
11,756 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Data Sources
- Workflow
- Key Rules
Scripts executed separately
../../../tools/arxiv_fetch.py../../../tools/deepxiv_fetch.py../../../tools/exa_search.py../../../tools/openalex_fetch.py../../../tools/semantic_scholar_fetch.py
Files
SKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytesSKILL.mdcore29,972 bytes../shared-references/fan-out-pattern.mddoc23,134 bytes../shared-references/integration-contract.mddoc19,930 bytes../shared-references/output-composition.mddoc5,293 bytes../../../tools/arxiv_fetch.pyruns11,762 bytes../../../tools/deepxiv_fetch.pyruns6,222 bytes../../../tools/exa_search.pyruns14,437 bytes../../../tools/openalex_fetch.pyruns12,106 bytes../../../tools/semantic_scholar_fetch.pyruns14,381 bytes
Read SKILL.md
# Research Literature Review
Research topic: $ARGUMENTS
## Constants
- **PAPER_LIBRARY** — Local directory containing user's paper collection (PDFs). Check these paths in order:
1. `papers/` in the current project directory
2. `literature/` in the current project directory
3. Custom path specified by user in `AGENTS.md` under `## Paper Library`
- **MAX_LOCAL_PAPERS = 20** — Maximum number of local PDFs to scan (read first 3 pages each). If more are found, prioritize by filename relevance to the topic.
- **SOURCES = `all`** — Which literature sources to search. Options: `zotero`, `obsidian`, `local`, `web`, `semantic-scholar`, `deepxiv`, `exa`, `gemini`, `openalex`, `all`. Full source table and selection rules: see `## Data Sources` below.
- **ARXIV_DOWNLOAD = false** — When `true`, download top 3-5 most relevant arXiv PDFs to PAPER_LIBRARY after search. When `false` (default), only fetch metadata (title, abstract, authors) via arXiv API — no files are downloaded.
- **ARXIV_MAX_DOWNLOAD = 5** — Maximum number of PDFs to download when `ARXIV_DOWNLOAD = true`.research-pipeline
When your agent uses it
Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
5,119 tokensWhen the skill is activated
Reference documents
15,529 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Optional formal proof route
- Constants
- Checkpoint execution rule
- Overview
- Resumable runs and heartbeat
- Pipeline
- Render HTML view (auto, when `RENDER_HTML = true`)
- Output Protocols
- Key Rules
- Typical Timeline
Scripts executed separately
../../../tools/iteration_log.py../../../tools/run_state.py../../../tools/watchdog.py
Files
../lean-formalize/SKILL.mddoc22,343 bytesSKILL.mdcore21,121 bytesSKILL.mdcore21,121 bytesSKILL.mdcore21,121 bytesSKILL.mdcore21,121 bytesSKILL.mdcore21,121 bytes../shared-references/external-cadence.mddoc20,174 bytes../shared-references/output-language.mddoc2,215 bytes../shared-references/output-manifest.mddoc1,753 bytes../shared-references/output-versioning.mddoc4,828 bytes../shared-references/resumable-runs.mddoc8,134 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../../tools/iteration_log.pyruns5,588 bytes../../../tools/run_state.pyruns18,500 bytes../../../tools/watchdog.pyruns19,054 bytes
Read SKILL.md
# Full Research Pipeline: Idea → Experiments → Submission
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **External cadence is fire-control only.** An overnight scheduler may checkresearch-refine
When your agent uses it
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
7,297 tokensWhen the skill is activated
Reference documents
5,599 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Constants
- State Persistence (Checkpoint Recovery)
- Output Structure
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytesSKILL.mdcore31,895 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/taste-calibration.mddoc4,819 bytes
Read SKILL.md
# Research Refine: Problem-Anchored, Elegant, Frontier-Aware Plan Refinement
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Refine and concretize: **$ARGUMENTS**research-refine-pipeline
When your agent uses it
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
1,603 tokensWhen the skill is activated
Reference documents
13,957 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Rule
- Default Outputs
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Files
../../shared-references/output-language.mddoc2,215 bytes../../shared-references/output-manifest.mddoc2,354 bytes../../shared-references/output-versioning.mddoc4,807 bytes../experiment-plan/SKILL.mddoc9,665 bytesSKILL.mdcore6,930 bytes../research-refine/SKILL.mddoc31,895 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Research Refine Pipeline: End-to-End Method and Experiment Planning
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Refine and concretize: **$ARGUMENTS**research-review
When your agent uses it
Get a deep critical review of research from a fresh Codex agent or a selected Gemini, Grok, or Claude Code reviewer. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,991 tokensWhen the skill is activated
Reference documents
5,762 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Context: $ARGUMENTS
- Prerequisites
- Workflow
- Key Rules
- Prompt Templates
Files
SKILL.mdcore9,163 bytes../shared-references/output-composition.mddoc5,293 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Research Review with a Selectable Reviewer
> **Codex assurance:** the fresh base reviewer is same-family. Record
> `review_independence: same-family` and `acceptance_status: provisional` in
> traces and deliverables. A selected reviewer can record cross-family accepted
> only after a completed, in-scope positive review with actual different model
> families; an unavailable reviewer is BLOCKED, never a fabricated PASS.
Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.
## Constants
- REVIEWER_MODEL = `gpt-6-astra` — Model used via a secondary Codex agent, reasoning effort `ultra` (deep-audit tier). Must be an OpenAI model (e.g., `gpt-6-astra`, `gpt-6.1-sol`)
- **REVIEWER_BACKEND = `codex`** — Default: a fresh Codex reviewer at the deep-audit tier (`ultra`). Resolve `— reviewer:`, project `.aris/reviewer.json`, then this default using `reviewer_route.py` (`--host codex --tier deep`), per [reviewer-backends.md](../shared-references/reviewer-backends.md). Gemini/Antigravity, Grok, and Claude Code use that contract at every call below; legacy `oracle-pro` rules remain in `reviewer-routing.md`.research-wiki
When your agent uses it
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
4,828 tokensWhen the skill is activated
Reference documents
8,385 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core Concepts
- Wiki Directory Structure
- Subcommands
- Integration with Existing Workflows
- Re-ideation Trigger
- Key Rules
- Acknowledgements
Scripts executed separately
../../../tools/capture_filter.py../../../tools/research_wiki.py
Files
SKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytesSKILL.mdcore17,991 bytes../shared-references/capture-antipatterns.mddoc5,259 bytes../shared-references/injection-hygiene.mddoc8,044 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/capture_filter.pyruns6,080 bytes../../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Research Wiki: Persistent Research Knowledge Base
Subcommand: **$ARGUMENTS**
## Overview
The research wiki is a persistent, per-project knowledge base that accumulates structured knowledge across the entire ARIS research lifecycle. Unlike one-off literature surveys that are used and forgotten, the wiki **compounds** — every paper read, idea tested, experiment run, and review received makes the wiki smarter.
Inspired by [Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): compile knowledge once, keep it current, don't re-derive on every query.
## Core Concepts
### Four Entity Types
resubmit-pipeline
When your agent uses it
Workflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says "resubmit pipeline", "重投流程", "port paper to <new venue>", "resubmit to <venue>", "tighten paper for resubmission", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
8,648 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- When to Use
- When NOT to Use
- Constants
- Inputs
- Pipeline
- Page-Shrink Heuristic
- Convergence Criteria (Phase 2 stop condition)
- Master `RESUBMIT_REPORT.md` Ledger
- Failure Modes
- Key Rules
- Output Contract
- Review Tracing
- Notes
Files
SKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytesSKILL.mdcore33,998 bytes../shared-references/reviewer-backends.mddoc9,712 bytes
Read SKILL.md
# Resubmit Pipeline: Text-Only Microedit Mode
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Compose a polished paper into a new venue under text-only constraints: **$ARGUMENTS**result-to-claim
When your agent uses it
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
3,304 tokensWhen the skill is activated
Reference documents
5,507 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- When to Use
- Workflow
- Rules
- Review Tracing
Scripts executed separately
../../../tools/evidence_check.py../../../tools/research_wiki.py
Files
SKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytesSKILL.mdcore13,324 bytes../shared-references/evidence-precheck.mddoc4,058 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../../../tools/evidence_check.pyruns9,970 bytes../../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Result-to-Claim Gate
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
> **Codex assurance:** deterministic evidence existence can be accepted, whilerun-experiment
When your agent uses it
Deploy and run ML experiments on local or remote GPU servers. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
2,279 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Key Rules
- AGENTS.md Example
Files
SKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytesSKILL.mdcore8,909 bytes../shared-references/compute-env-contract.mddoc10,577 bytes
Read SKILL.md
# Run Experiment
Deploy and run ML experiment: $ARGUMENTS
## Workflow
### Step 1: Detect Environment
Read the project's `AGENTS.md` to determine the experiment environment:
- **Local GPU**: Look for local CUDA/MPS setup info
- **Remote server**: Look for SSH alias, conda env, code directory
- **Vast.ai instance**: Look for `gpu: vast`, `vast_instance`, SSH host/port, remote path, and optional `auto_destroy`
- **Modal serverless**: Look for `gpu: modal`, app/function name, image/dependency setup, and secretssemantic-scholar
When your agent uses it
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,978 tokensWhen the skill is activated
Reference documents
5,148 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role & Positioning
- Constants
- Workflow
- Key Rules
Scripts executed separately
../../../tools/research_wiki.py../../../tools/semantic_scholar_fetch.py
Files
SKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytesSKILL.mdcore10,438 bytes../shared-references/integration-contract.mddoc19,930 bytes../../../tools/research_wiki.pyruns78,927 bytes../../../tools/semantic_scholar_fetch.pyruns14,381 bytes
Read SKILL.md
# Semantic Scholar Paper Search
Search topic or paper ID: $ARGUMENTS
## Role & Positioning
This skill is the **published venue** counterpart to `/arxiv`:
| Skill | Source | Best for |
|-------|--------|----------|
| `/arxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |
| `/semantic-scholar` | Semantic Scholar API | **Published** journal/conference papers (IEEE, ACM, Springer, etc.) with citation counts, venue info, TLDR |
**Do NOT duplicate arXiv's job.** If results contain an `externalIds.ArXiv` field, the paper is also on arXiv — note this but do not re-fetch from arXiv.serverless-modal
When your agent uses it
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
3,535 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Authentication
- Pricing (source: modal.com/pricing, per-second billing)
- !! Cost Estimation Required !!
- Workflow
- CLI Reference
- Key Tips
- Composing with Other Skills
- AGENTS.md Example
- Documentation
Files
SKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytesSKILL.mdcore13,169 bytes../shared-references/compute-env-contract.mddoc10,577 bytes
Read SKILL.md
# Modal Cloud GPU — Training & Inference
Task: $ARGUMENTS
## Overview
**Modal** is a serverless GPU cloud. Key advantages over SSH-based platforms (vast.ai, remote servers):
- **Zero config**: no SSH, no Docker, no port forwarding. Write Python → `modal run` → done.
- **Auto scale-to-zero**: billing stops the instant your code finishes. No idle instances.
- **Local-first**: run `modal run` from your laptop. Code, data, and results stay local; only the GPU function runs remotely.
- **Reproducible environments**: dependencies declared in code via `modal.Image`, not system-level packages.
Treat the `modal.Image` chain as the RENDERED form of the declarative env spec in
`../shared-references/compute-env-contract.md` — same spec fields (base, ordered
pip phases, env vars, smoke probes), same `env:<name>@<specHash>` ledger entry inslides-polish
When your agent uses it
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic style leaks, fixes text-frame overflow, and catches per-slide layout drift. Trigger phrases: "polish slides", "slides 排版不对", "PPTX 字体太小", "和 Beamer 比一下", "per-page review", "和 codex 一页一页过".
What it loads into context
Frontmatter
313 tokensAlways available to the agent
SKILL.md
7,865 tokensWhen the skill is activated
Reference documents
9,198 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What This Skill Is — and Is NOT
- Constants
- Prerequisites
- Inputs
- Output Layout
- Workflow
- Style Presets
- Effort Levels
- Hard Invariants
- Review Tracing
- Prior Skill Relationship
- When NOT to Use
- Empirical Origin
- Parameter Pass-Through
Files
../shared-references/effort-contract.mddoc5,999 bytes../shared-references/experiment-integrity.mddoc2,355 bytes../shared-references/review-tracing.mddoc9,517 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc1,809 bytes../shared-references/reviewer-routing.mddoc8,348 bytesSKILL.mdcore29,646 bytesSKILL.mdcore29,646 bytesSKILL.mdcore29,646 bytesSKILL.mdcore29,646 bytesSKILL.mdcore29,646 bytesSKILL.mdcore29,646 bytesSKILL.mdcore29,646 bytes
Read SKILL.md
# Slides Polish: Per-Page Codex Review + Targeted Layout Fixes
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Polish a generated slide deck — Beamer (`.tex` + `.pdf`) and/or PPTX — byspecification-writing
When your agent uses it
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
2,211 tokensWhen the skill is activated
Reference documents
6,374 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
../shared-references/patent-format-cn.mddoc9,352 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytesSKILL.mdcore9,699 bytes
Read SKILL.md
# Specification Writing: Section-by-Section Patent Description
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Write the patent specification based on: **$ARGUMENTS**system-profile
When your agent uses it
Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,020 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
Files
SKILL.mdcore4,473 bytes
Read SKILL.md
# System Profile
Profile the specified target and summarize the results. Target: $ARGUMENTS
## Instructions
You are a profiling assistant. Based on the user's target, choose appropriate profiling strategies, **including writing instrumentation code when needed**, then run profiling, analyze results, and produce a summary.
### Step 1: Determine the profiling target
Parse `$ARGUMENTS` to understand what to profile. Examples:
- A Python script or module
- A running process (PID or service name)
- A specific function or code blocktraining-check
When your agent uses it
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
1,234 tokensWhen the skill is activated
Reference documents
2,176 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs To Establish First
- Per-Round Check
- Stop Behavior
- Interactive Loop Guidance
Files
../shared-references/reviewer-backends.mddoc9,712 bytesSKILL.mdcore5,617 bytesSKILL.mdcore5,617 bytes
Read SKILL.md
# Training Check
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Codex default (fresh native reviewer)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
You are now in **interactive watch** / 交互式训练监控模式.vast-gpu
When your agent uses it
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
4,329 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- State File
- Workflow
- Key Rules
- AGENTS.md Example
- Composing with Other Skills
Files
../shared-references/compute-env-contract.mddoc10,577 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytes
Read SKILL.md
# Vast.ai GPU Management
Manage vast.ai GPU instance: $ARGUMENTS
## Overview
Rent cheap, capable GPUs from vast.ai on demand. This skill **analyzes the training task** to determine GPU requirements, searches for the best-value offers, presents options with estimated total cost, and handles the full lifecycle: rent → setup → run → destroy.
Users do NOT specify GPU models or hardware. They describe the task — the skill figures out what to rent.
**Prerequisites:** The `vastai` CLI must be installed (requires **Python ≥ 3.10**) and authenticated:
```bash
pip install vastai
vastai set api-key YOUR_API_KEYweb-debug-search
When your agent uses it
Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
3,331 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope and evidence boundary
- Step 1: Parse the request and overrides
- Step 2: Route source profiles
- Step 3: Search with bounded queries
- Step 4: Classify each result on four independent axes
- Step 5: Deduplicate and synthesize
- Step 6: Report actionable results
- Failure handling
- Required closing notice
Files
SKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytes
Read SKILL.md
# Web Debug Search
Debugging query: **$ARGUMENTS**
## Scope and evidence boundary
Use this skill to find prior reports, compatibility clues, technical Q&A, and
community workarounds across non-academic web sources. It is a
**debugging/discovery** workflow, not a literature-search workflow. Never add
its results to a bibliography, cite them as support for a paper claim, or
present a community post as peer-reviewed evidence.
Supported source profiles:
wiki-enrich
When your agent uses it
Fill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers/ as TODO scaffolds.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
4,444 tokensWhen the skill is activated
Reference documents
511 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this skill exists
- Constants
- Pre-flight
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Scripts executed separately
../../../tools/research_wiki.py
Files
../shared-references/output-language.mddoc2,215 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytesSKILL.mdcore16,776 bytes../../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Wiki Enrich: Fill Paper TODO Sections (Karpathy LLM-Wiki)
Target: **$ARGUMENTS**
## Why this skill exists
`ingest_paper` (called by `/research-lit`, `/arxiv`, `/alphaxiv`, `/deepxiv`, `/semantic-scholar`, `/exa-search`, `/firecrawl-search`) only renders the per-paper scaffold — frontmatter + abstract + **10 fillable** `_TODO._` placeholder sections (plus two protected sections: `## Connections` is graph-summary and `## Abstract (original)` is auto-populated when `--arxiv-id` is given). No downstream skill in ARIS fills those 10 sections; the wiki sits as TODO until someone reads each paper.
This contradicts the Karpathy LLM-wiki design (https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f):
> "You never (or rarely) write the wiki yourself — the LLM writes and maintains all of it. … The tedious part of maintaining a knowledge base is not the reading or the thinking — it's the bookkeeping. … LLMs don't get bored, don't forget to update a cross-reference, and can touch 15 files in one pass."
`/wiki-enrich` is the missing back half of `ingest_paper`: it reads each scaffolded paper page, fetches paper content from external sources via a graceful fallback chain (see Phase 2.3 for the full 5-source chain), and rewrites the 10 fillable TODO sections into 1-3 sentence prose summaries.
writing-systems-papers
When your agent uses it
Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure", "OSDI paper", "SOSP paper", or wants fine-grained structural guidance for a systems conference submission.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,759 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Relationship to Other ARIS Skills
- Page Allocation: 12-Page Systems Paper
- Section Blueprints
- Writing Patterns
- Conference Differences
- Workflow
- Quick Self-Check
- Academic Integrity
- Authoritative Sources
Files
SKILL.mdcore6,859 bytes
Read SKILL.md
# Writing Systems Papers: Paragraph-Level Blueprint
Structural guidance for **$ARGUMENTS**
## Relationship to Other ARIS Skills
- **paper-write**: General paper generation workflow with citation verification. This skill complements it with systems-specific structural blueprints.
- **paper-slides**: Conference presentation generation (Beamer+PPTX). Already covers talks — no overlap.
- **paper-plan**: Research outline creation. Use paper-plan first, then this skill for paragraph-level structure.
**Boundary**: paper-write handles the generation workflow (LaTeX output, DBLP verification, section-by-section drafting). This skill provides the **structural skeleton** — page budgets, paragraph roles, and writing patterns specific to systems venues.
---
slides-polish
When your agent uses it
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic style leaks, fixes text-frame overflow, and catches per-slide layout drift. Trigger phrases: "polish slides", "slides 排版不对", "PPTX 字体太小", "和 Beamer 比一下", "per-page review", "和 codex 一页一页过".
What it loads into context
Frontmatter
319 tokensAlways available to the agent
SKILL.md
7,919 tokensWhen the skill is activated
Reference documents
24,418 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What This Skill Is — and Is NOT
- Constants
- Prerequisites
- Inputs
- Output Layout
- Workflow
- Style Presets
- Effort Levels
- Hard Invariants
- Review Tracing
- Prior Skill Relationship
- When NOT to Use
- Empirical Origin
- Parameter Pass-Through
Files
../shared-references/effort-contract.mddoc8,352 bytes../shared-references/experiment-integrity.mddoc2,355 bytes../shared-references/review-tracing.mddoc23,757 bytes../shared-references/reviewer-backends.mddoc9,712 bytes../shared-references/reviewer-independence.mddoc3,473 bytes../shared-references/reviewer-routing.mddoc52,492 bytesSKILL.mdcore29,720 bytesSKILL.mdcore29,720 bytesSKILL.mdcore29,720 bytesSKILL.mdcore29,720 bytesSKILL.mdcore29,720 bytesSKILL.mdcore29,720 bytesSKILL.mdcore29,720 bytes
Read SKILL.md
# Slides Polish: Per-Page Codex Review + Targeted Layout Fixes
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Polish a generated slide deck — Beamer (`.tex` + `.pdf`) and/or PPTX — byspecification-writing
When your agent uses it
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
2,243 tokensWhen the skill is activated
Reference documents
6,374 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Constants
- Inputs
- Shared References
- Workflow
- Key Rules
Files
../shared-references/patent-format-cn.mddoc9,352 bytes../shared-references/patent-writing-principles.mddoc9,032 bytes../shared-references/reviewer-backends.mddoc9,712 bytesSKILL.mdcore9,722 bytes
Read SKILL.md
# Specification Writing: Section-by-Section Patent Description
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Write the patent specification based on: **$ARGUMENTS**system-profile
When your agent uses it
Profile a target (script, process, GPU, memory, interconnect) for performance analysis. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,020 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Instructions
Files
SKILL.mdcore4,473 bytes
Read SKILL.md
# System Profile
Profile the specified target and summarize the results. Target: $ARGUMENTS
## Instructions
You are a profiling assistant. Based on the user's target, choose appropriate profiling strategies, **including writing instrumentation code when needed**, then run profiling, analyze results, and produce a summary.
### Step 1: Determine the profiling target
Parse `$ARGUMENTS` to understand what to profile. Examples:
- A Python script or module
- A running process (PID or service name)
- A specific function or code blocktraining-check
When your agent uses it
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
What it loads into context
Frontmatter
190 tokensAlways available to the agent
SKILL.md
1,654 tokensWhen the skill is activated
Reference documents
6,768 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context: $ARGUMENTS
- Constants
- When to Use
- Workflow
- Integration with Watchdog
- Rules
- CronCreate Setup Example
Scripts executed separately
../../tools/watchdog.py
Files
../shared-references/external-cadence.mddoc19,084 bytes../shared-references/reviewer-backends.mddoc9,712 bytesSKILL.mdcore6,871 bytesSKILL.mdcore6,871 bytesSKILL.mdcore6,871 bytes../../tools/watchdog.pyruns19,054 bytes
Read SKILL.md
# Training Check
> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.
Periodically read WandB metrics during training to catch problems early. Do not wait until training finishes to discover it was a waste of GPU time.vast-gpu
When your agent uses it
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
4,331 tokensWhen the skill is activated
Reference documents
2,646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- State File
- Workflow
- Key Rules
- CLAUDE.md Example
- Composing with Other Skills
Files
../shared-references/compute-env-contract.mddoc10,567 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytesSKILL.mdcore15,737 bytes
Read SKILL.md
# Vast.ai GPU Management
Manage vast.ai GPU instance: $ARGUMENTS
## Overview
Rent cheap, capable GPUs from vast.ai on demand. This skill **analyzes the training task** to determine GPU requirements, searches for the best-value offers, presents options with estimated total cost, and handles the full lifecycle: rent → setup → run → destroy.
Users do NOT specify GPU models or hardware. They describe the task — the skill figures out what to rent.
**Prerequisites:** The `vastai` CLI must be installed (requires **Python ≥ 3.10**) and authenticated:
```bash
pip install vastai
vastai set api-key YOUR_API_KEYweb-debug-search
When your agent uses it
Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
3,331 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope and evidence boundary
- Step 1: Parse the request and overrides
- Step 2: Route source profiles
- Step 3: Search with bounded queries
- Step 4: Classify each result on four independent axes
- Step 5: Deduplicate and synthesize
- Step 6: Report actionable results
- Failure handling
- Required closing notice
Files
SKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytesSKILL.mdcore15,068 bytes
Read SKILL.md
# Web Debug Search
Debugging query: **$ARGUMENTS**
## Scope and evidence boundary
Use this skill to find prior reports, compatibility clues, technical Q&A, and
community workarounds across non-academic web sources. It is a
**debugging/discovery** workflow, not a literature-search workflow. Never add
its results to a bibliography, cite them as support for a paper claim, or
present a community post as peer-reviewed evidence.
Supported source profiles:
wiki-enrich
When your agent uses it
Fill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers/ as TODO scaffolds.
What it loads into context
Frontmatter
148 tokensAlways available to the agent
SKILL.md
4,406 tokensWhen the skill is activated
Reference documents
512 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this skill exists
- Constants
- Pre-flight
- Workflow
- Output Protocols
- Key Rules
- Composing with Other Skills
Scripts executed separately
../../tools/research_wiki.py
Files
../shared-references/output-language.mddoc2,215 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytesSKILL.mdcore16,628 bytes../../tools/research_wiki.pyruns78,927 bytes
Read SKILL.md
# Wiki Enrich: Fill Paper TODO Sections (Karpathy LLM-Wiki)
Target: **$ARGUMENTS**
## Why this skill exists
`ingest_paper` (called by `/research-lit`, `/arxiv`, `/alphaxiv`, `/deepxiv`, `/semantic-scholar`, `/exa-search`, `/firecrawl-search`) only renders the per-paper scaffold — frontmatter + abstract + **10 fillable** `_TODO._` placeholder sections (plus two protected sections: `## Connections` is graph-summary and `## Abstract (original)` is auto-populated when `--arxiv-id` is given). No downstream skill in ARIS fills those 10 sections; the wiki sits as TODO until someone reads each paper.
This contradicts the Karpathy LLM-wiki design (https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f):
> "You never (or rarely) write the wiki yourself — the LLM writes and maintains all of it. … The tedious part of maintaining a knowledge base is not the reading or the thinking — it's the bookkeeping. … LLMs don't get bored, don't forget to update a cross-reference, and can touch 15 files in one pass."
`/wiki-enrich` is the missing back half of `ingest_paper`: it reads each scaffolded paper page, fetches paper content from external sources via a graceful fallback chain (see Phase 2.3 for the full 5-source chain), and rewrites the 10 fillable TODO sections into 1-3 sentence prose summaries.
writing-systems-papers
When your agent uses it
Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure", "OSDI paper", "SOSP paper", or wants fine-grained structural guidance for a systems conference submission.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
1,779 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Relationship to Other ARIS Skills
- Page Allocation: 12-Page Systems Paper
- Section Blueprints
- Writing Patterns
- Conference Differences
- Workflow
- Quick Self-Check
- Academic Integrity
- Authoritative Sources
Files
SKILL.mdcore6,903 bytes
Read SKILL.md
# Writing Systems Papers: Paragraph-Level Blueprint
Structural guidance for **$ARGUMENTS**
## Relationship to Other ARIS Skills
- **paper-write**: General paper generation workflow with citation verification. This skill complements it with systems-specific structural blueprints.
- **paper-slides**: Conference presentation generation (Beamer+PPTX). Already covers talks — no overlap.
- **paper-plan**: Research outline creation. Use paper-plan first, then this skill for paragraph-level structure.
**Boundary**: paper-write handles the generation workflow (LaTeX output, DBLP verification, section-by-section drafting). This skill provides the **structural skeleton** — page budgets, paragraph roles, and writing patterns specific to systems venues.
---
Skills included
- ablation-planner
- alphaxiv
- analyze-results
- arxiv
- auto-paper-improvement-loop
- auto-review-loop
- auto-review-loop-llm
- auto-review-loop-minimax
- citation-audit
- citation-crosscheck
- claims-drafting
- comm-lit-review
- deepxiv
- dse-loop
- embodiment-description
- exa-search
- experiment-audit
- experiment-bridge
- experiment-plan
- experiment-queue
- feishu-notify
- figure-description
- figure-spec
- firecrawl-search
- formula-derivation
- gemini-search
- grant-proposal
- idea-creator
- idea-discovery
- idea-discovery-robot
- integrity-forensics
- interview-cheatsheet
- invention-structuring
- jurisdiction-format
- keenable-search
- kill-argument
- lean-formalize
- mermaid-diagram
- meta-apply
- meta-optimize
- monitor-experiment
- novelty-check
- openalex
- overleaf-sync
- paper-claim-audit
- paper-compile
- paper-figure
- paper-illustration
- paper-illustration-image2
- paper-plan
- paper-poster
- paper-poster-html
- paper-slides
- paper-talk
- paper-write
- paper-writing
- patent-novelty-check
- patent-pipeline
- patent-review
- pixel-art
- prior-art-search
- proof-checker
- proof-orchestrator
- proof-writer
- qzcli
- rebuttal
- render-html
- research-implement-feature
- research-lit
- research-pipeline
- research-refine
- research-refine-pipeline
- research-review
- research-wiki
- resubmit-pipeline
- result-to-claim
- run-experiment
- semantic-scholar
- serverless-modal
- auto-paper-improvement-loop
- auto-review-loop
- novelty-check
- paper-figure
- paper-plan
- paper-write
- research-refine
- research-review
- auto-paper-improvement-loop
- auto-review-loop
- grant-proposal
- idea-creator
- idea-discovery
- idea-discovery-robot
- novelty-check
- paper-figure
- paper-plan
- paper-poster-html
- paper-slides
- paper-write
- paper-writing
- research-refine
- research-review
- ablation-planner
- alphaxiv
- analyze-results
- arxiv
- auto-paper-improvement-loop
- auto-review-loop
- auto-review-loop-llm
- auto-review-loop-minimax
- citation-audit
- citation-crosscheck
- claims-drafting
- comm-lit-review
- deepxiv
- dse-loop
- embodiment-description
- exa-search
- experiment-audit
- experiment-bridge
- experiment-plan
- experiment-queue
- feishu-notify
- figure-description
- figure-spec
- firecrawl-search
- formula-derivation
- gemini-search
- grant-proposal
- idea-creator
- idea-discovery
- idea-discovery-robot
- integrity-forensics
- interview-cheatsheet
- invention-structuring
- jurisdiction-format
- keenable-search
- kill-argument
- lean-formalize
- mermaid-diagram
- meta-apply
- meta-optimize
- monitor-experiment
- novelty-check
- openalex
- overleaf-sync
- paper-claim-audit
- paper-compile
- paper-figure
- paper-illustration
- paper-illustration-image2
- paper-plan
- paper-poster
- paper-poster-html
- paper-slides
- paper-talk
- paper-write
- paper-writing
- patent-novelty-check
- patent-pipeline
- patent-review
- pixel-art
- prior-art-search
- proof-checker
- proof-orchestrator
- proof-writer
- qzcli
- rebuttal
- render-html
- research-implement-feature
- research-lit
- research-pipeline
- research-refine
- research-refine-pipeline
- research-review
- research-wiki
- resubmit-pipeline
- result-to-claim
- run-experiment
- semantic-scholar
- serverless-modal
- slides-polish
- specification-writing
- system-profile
- training-check
- vast-gpu
- web-debug-search
- wiki-enrich
- writing-systems-papers
- slides-polish
- specification-writing
- system-profile
- training-check
- vast-gpu
- web-debug-search
- wiki-enrich
- writing-systems-papers
Repository facts
- License
- MIT
- Created
- Mar 10, 2026
- Last pushed
- Nov 6, 2026
- Forks
- 1,527
- Open issues
- 57
- Project activity
- Active
Rank over the last 12 weeks
Now #100 · best #97 · up 1 in 30 days
- #103 from Oct 23 to Oct 25
- #100 from Oct 28 to Oct 29
- #101 from Oct 30 to Oct 31
- #100 from Nov 1 to Nov 3
- #99 from Nov 4 to Nov 6
- #100 since Nov 7
28 earlier periods
- #96 on Aug 2
- #97 from Aug 8 to Aug 9
- #98 from Aug 10 to Aug 12
- #99 from Aug 13 to Aug 15
- #98 from Aug 16 to Aug 21
- #97 on Aug 22
- #98 on Aug 23
- #99 from Aug 24 to Aug 25
- #100 from Aug 26 to Aug 29
- #99 from Aug 30 to Aug 31
- #100 from Sep 1 to Sep 2
- #101 on Sep 3
- #100 on Sep 4
- #101 on Sep 5
- #100 on Sep 6
- #101 from Sep 7 to Sep 15
- #100 on Sep 16
- #101 on Sep 17
- #102 from Sep 18 to Sep 19
- #103 from Sep 20 to Sep 22
- #102 from Sep 23 to Sep 25
- #101 on Sep 26
- #102 from Sep 27 to Sep 29
- #101 on Sep 30
- #102 from Oct 1 to Oct 5
- #100 on Oct 6
- #101 from Oct 7 to Oct 19
- #102 from Oct 20 to Oct 22
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1,596 notes
skills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/alphaxiv/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtools/install_aris.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedtools/install_aris.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 144 broad permissionsin 131 files: skills/lean-formalize/SKILL.md:1 integrity-forensics/SKILL.md:1 experiment-plan/SKILL.md:1 and 128 more
- 785 dangerous shell commandsin 17 files: tools/install_aris.sh:401 paper-write/templates/aaai2026.tex:121 skills/shared-references/reviewer-routing.md:771 and 14 more
- 1,734 network referencesin 137 files: tools/research_wiki.py:78 tools/arxiv_fetch.py:34 tools/extract_paper_style.py:58 and 134 more
- 14 obfuscation signalsin 7 files: tools/threat_scan.py:108 mermaid-diagram/SKILL.md:99 render-html/scripts/render_html.py:247 and 4 more
- 2 instruction override signalsin 1 file: tools/threat_scan.py:32
- 448 executable scriptsin 54 files: tools/install_aris.sh:1 tools/research_wiki.py:1 tools/skill_picker.py:1 and 51 more
- 287 references to secretsin 53 files: tools/openalex_fetch.py:29 tools/research_wiki.py:93 skills/shared-references/reviewer-routing.md:166 and 50 more
- No requests to vote in Hot
Show all 3,414 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://json.schemastore.org/claude-code-marketplace.json", - Network accessline 2
"$schema": "https://json.schemastore.org/claude-code-marketplace.json", - Network accessline 4
"owner": { "name": "wanshuiyin", "url": "https://github.com/wanshuiyin" - Network accessline 5
"name": "wanshuiyin", "url": "https://github.com/wanshuiyin" }, - Network accessline 6
"url": "https://github.com/wanshuiyin" - Network accessline 16
"author": { "name": "wanshuiyin", "url": "https://github.com/wanshuiyin" - Network accessline 17
"name": "wanshuiyin", "url": "https://github.com/wanshuiyin" }, - Network accessline 18
"url": "https://github.com/wanshuiyin" - Network accessline 19
}, "homepage": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep", "repository": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep", - Network accessline 20
"homepage": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep", - Network accessline 21
"repository": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep",
.claude-plugin/plugin.json
- Network accessline 1
{ "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json", - Network accessline 2
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json", - Network accessline 5
"author": { "name": "wanshuiyin", "url": "https://github.com/wanshuiyin" - Network accessline 6
"name": "wanshuiyin", "url": "https://github.com/wanshuiyin" }, - Network accessline 7
"url": "https://github.com/wanshuiyin" - Network accessline 8
}, "homepage": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep", "repository": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep", - Network accessline 9
"homepage": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep", - Network accessline 10
"repository": "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep",
skills/ablation-planner/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply
skills/alphaxiv/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Glob - Network accessline 12
> Quick single-paper reader with tiered source fallback (overview → full markdown → LaTeX source). Powered by [AlphaXiv](https://www.alphaxiv.org). - Network accessline 29
- **OVERVIEW_URL** = `https://www.alphaxiv.org/overview/{PAPER_ID}.md` - Network accessline 30
- **ABS_URL** = `https://www.alphaxiv.org/abs/{PAPER_ID}.md` - Network accessline 31
- **ARXIV_SRC_URL** = `https://arxiv.org/src/{PAPER_ID}` - Network accessline 34
> Overrides (append to arguments): > - `/alphaxiv 2401.12345` — quick overview > - `/alphaxiv "https://arxiv.org/abs/2401.12345"` — auto-extract ID - Network accessline 35
> - `/alphaxiv 2401.12345` — quick overview > - `/alphaxiv "https://arxiv.org/abs/2401.12345"` — auto-extract ID > - `/alphaxiv 2401.12345 - depth: src` — force LaTeX source inspection - Network accessline 36
> - `/alphaxiv "https://arxiv.org/abs/2401.12345"` — auto-extract ID - Network accessline 46
- `https://arxiv.org/abs/2401.12345` or `https://arxiv.org/abs/2401.12345v2` - Network accessline 47
- `https://arxiv.org/pdf/2401.12345` - Network accessline 48
- `https://alphaxiv.org/overview/2401.12345` or `https://www.alphaxiv.org/overview/2401.12345` - Network accessline 49
- `https://alphaxiv.org/abs/2401.12345` or `https://www.alphaxiv.org/abs/2401.12345` - Network accessline 62
curl -sL --max-time 15 -A "{ALPHAXIV_UA}" "https://www.alphaxiv.org/overview/{PAPER_ID}.md" - Network accessline 76
curl -sL --max-time 15 -A "{ALPHAXIV_UA}" "https://www.alphaxiv.org/abs/{PAPER_ID}.md" - Network accessline 88
When the overview and full markdown are both insufficient (e.g., the user asks about equations, proofs, appendix details, or implementation specifics), download the paper's LaTeX source from `https://arxiv.org/src/{PAPER_ID}`. - Network accessline 109
- **arXiv**: [PAPER_ID] — https://arxiv.org/abs/[PAPER_ID]
skills/analyze-results/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit
skills/arxiv/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 76
NS = "http://www.w3.org/2005/Atom" query = urllib.parse.quote("QUERY") - Network accessline 77
query = urllib.parse.quote("QUERY") url = (f"http://export.arxiv.org/api/query" f"?search_query={query}&start=0&max_results=MAX_RESULTS" - Network accessline 78
url = (f"http://export.arxiv.org/api/query" - Network accessline 79
f"?search_query={query}&start=0&max_results=MAX_RESULTS" f"&sortBy=relevance&sortOrder=descending") with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 80
f"&sortBy=relevance&sortOrder=descending") with urllib.request.urlopen(url, timeout=30) as r: root = ET.fromstring(r.read()) - Network accessline 81
with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 96
"published": published, "categories": cats, "pdf_url": f"https://arxiv.org/pdf/{aid}.pdf", - Network accessline 97
"categories": cats, "pdf_url": f"https://arxiv.org/pdf/{aid}.pdf", "abs_url": f"https://arxiv.org/abs/{aid}", - Network accessline 98
"pdf_url": f"https://arxiv.org/pdf/{aid}.pdf", - Network accessline 99
"abs_url": f"https://arxiv.org/abs/{aid}", - Network accessline 120
python3 -c " import urllib.request, xml.etree.ElementTree as ET NS = 'http://www.w3.org/2005/Atom' - Network accessline 121
import urllib.request, xml.etree.ElementTree as ET NS = 'http://www.w3.org/2005/Atom' url = 'http://export.arxiv.org/api/query?id_list=ARXIV_ID' - Network accessline 122
NS = 'http://www.w3.org/2005/Atom' url = 'http://export.arxiv.org/api/query?id_list=ARXIV_ID' with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 123
url = 'http://export.arxiv.org/api/query?id_list=ARXIV_ID' with urllib.request.urlopen(url, timeout=30) as r: root = ET.fromstring(r.read()) - Network accessline 124
with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 148
print(f'Already exists: {out}') sys.exit(0) req = urllib.request.Request( - Network accessline 149
sys.exit(0) req = urllib.request.Request( 'https://arxiv.org/pdf/ARXIV_ID.pdf', - Network accessline 150
req = urllib.request.Request( - Network accessline 151
'https://arxiv.org/pdf/ARXIV_ID.pdf', - Network accessline 152
headers={'User-Agent': 'arxiv-skill/1.0'}, ) with urllib.request.urlopen(req, timeout=60) as r: - Network accessline 153
) with urllib.request.urlopen(req, timeout=60) as r: out.write_bytes(r.read()) - Network accessline 154
with urllib.request.urlopen(req, timeout=60) as r:
skills/auto-paper-improvement-loop/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-r
skills/auto-review-loop-llm/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, Skill - Network accessline 44
[Credential-related source omitted] - Network accessline 45
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 46
"LLM_BASE_URL": "https://api.deepseek.com/v1", - Network accessline 56
| Provider | LLM_BASE_URL | LLM_MODEL | |----------|--------------|-----------| | **OpenAI** | `https://api.openai.com/v1` | `gpt-6.1-sol`, `gpt-6-astra` | - Network accessline 57
|----------|--------------|-----------| | **OpenAI** | `https://api.openai.com/v1` | `gpt-6.1-sol`, `gpt-6-astra` | | **DeepSeek** | `https://api.deepseek.com/v1` | `deepseek-chat`, `deepseek-reasoner` | - Network accessline 58
| **OpenAI** | `https://api.openai.com/v1` | `gpt-6.1-sol`, `gpt-6-astra` | - Network accessline 59
| **DeepSeek** | `https://api.deepseek.com/v1` | `deepseek-chat`, `deepseek-reasoner` | - Network accessline 60
| **MiniMax** | `https://api.minimax.io/v1` | `MiniMax-M3` | - Network accessline 61
| **Kimi (Moonshot)** | `https://api.moonshot.cn/v1` | `moonshot-v1-8k`, `moonshot-v1-32k` | - Network accessline 62
| **ZhiPu (GLM)** | `https://open.bigmodel.cn/api/paas/v4` | `glm-4`, `glm-4-plus` | - Network accessline 63
| **SiliconFlow** | `https://api.siliconflow.cn/v1` | `Qwen/Qwen2.5-72B-Instruct` | - Network accessline 64
| **阿里云百炼** | `https://dashscope.aliyuncs.com/compatible-mode/v1` | `qwen-max` | - Network accessline 65
| **零一万物** | `https://api.lingyiwanwu.com/v1` | `yi-large` | - Network accessline 91
[Credential-related source omitted] - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Network accessline 107
[Credential-related source omitted] - Access to secretsline 107
[Credential-related source omitted] - Access to secretsline 109
[Credential-related source omitted] - Network accessline 172
[Credential-related source omitted] - Access to secretsline 172
[Credential-related source omitted] - Access to secretsline 174
[Credential-related source omitted] - Network accessline 247
- Document everything - Include previous context in round 2+ prompts - Prefer MCP tool over curl when available - Network accessline 249
- Prefer MCP tool over curl when available
skills/auto-review-loop-minimax/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, Skill - Network accessline 47
### Method 2: curl (Fallback) - Network accessline 49
If MCP is not available, use curl directly: - Network accessline 52
[Credential-related source omitted] - Access to secretsline 52
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Network accessline 67
**Why MiniMax instead of Codex MCP?** Codex CLI uses OpenAI's Responses API (`/v1/responses`) which is not supported by third-party providers. See: https://github.com/openai/codex/discussions/7782 - Network accessline 126
[Credential-related source omitted] - Access to secretsline 126
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Network accessline 237
- Update project notes after each round, not just at the end - For round 2+, always include previous review context in the prompt - Prefer MCP tool over curl when available (more reliable) - Network accessline 239
- Prefer MCP tool over curl when available (more reliable) - Network accessline 276
**curl Fallback:** - Network accessline 278
[Credential-related source omitted] - Access to secretsline 278
[Credential-related source omitted] - Access to secretsline 280
[Credential-related source omitted]
skills/auto-review-loop/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, Skill, Task, mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__gr - Dangerous shell operationline 513
##### Nightmare — Codex Exec (GPT reads repo directly) - Dangerous shell operationline 784
trap 'rm -f "$PROMPTFILE"' EXIT - Network accessline 1038
Codex/manual finalizer; caller-declared identity remains unverified. - Save `threadId` (codex/manual), fresh evidence path/ID (`copilot-native`), or `reviewer_profile` (compatibility copilot); use the appropriate continuation mechanism - ** - Network accessline 1039
- Save `threadId` (codex/manual), fresh evidence path/ID (`copilot-native`), or `reviewer_profile` (compatibility copilot); use the appropriate continuation mechanism - **Anti-hallucination citations**: When adding references during fixes, - Network accessline 1040
- **Anti-hallucination citations**: When adding references during fixes, NEVER fabricate BibTeX. Use the same DBLP → CrossRef → `[VERIFY]` chain as `/paper-write`: (1) `curl -s "https://dblp.org/search/publ/api?q=TITLE&format=json"` → get k - Dangerous shell operationline 1081
trap 'rm -f "$PROMPTFILE"' EXIT
skills/citation-audit/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Edit, Write, mcp__codex__codex, WebSearch, WebFetch, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__revi
skills/citation-crosscheck/SKILL.md
skills/citation-crosscheck/scripts/cx_verify.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 18
ESCALATE routed to the main agent's own primary-source fetch (Step 4) - Network accessline 157
The namespace is KEPT. Stripping both the doi.org and the arxiv.org wrappers to a bare id made 'https://arxiv.org/abs/2301.1' and 'https://doi.org/2301.1' compare - Network accessline 158
bare id made 'https://arxiv.org/abs/2301.1' and 'https://doi.org/2301.1' compare - Network accessline 161
A wrapper with nothing after it ('doi:', 'https://doi.org/') yields '', and an empty - Network accessline 1114
("page range boundary moved", _entry(*_both(pages='1-234', web_pages='12-34')), 'ESCALATE'), ("dash style is still cosmetic", _entry(*_both(pages='12-20', web_pages='12--20')), 'MATCH'), ("arxiv wrapper vs doi wrapper", _entry(*_bot - Network accessline 1115
("dash style is still cosmetic", _entry(*_both(pages='12-20', web_pages='12--20')), 'MATCH'), ("arxiv wrapper vs doi wrapper", _entry(*_both(doi='https://arxiv.org/abs/2301.00001', web_ - Network accessline 1116
("arxiv wrapper vs doi wrapper", _entry(*_both(doi='https://arxiv.org/abs/2301.00001', - Network accessline 1117
web_doi='https://doi.org/2301.00001')), 'ESCALATE'), - Network accessline 1118
("doi resolver prefix is cosmetic", _entry(*_both(doi='https://doi.org/10.1/abc', web_doi='10.1/abc')), 'MATCH'), - Network accessline 1119
("empty identifier is not an identifier", _entry(*_both(doi='doi:', web_doi='https://doi.org/')), 'ESCALATE'), - Network accessline 1144
("same arXiv id in venue, cosmetic form", _entry(*_both(venue='arXiv:2401.00001', web_venue='arxiv 2401.00001')), 'MATCH'), ("preprint-with-id vs known published", _entry(*_both(venue='arXiv:2401.00001', web_venue='ICML')), 'MINOR'), - Network accessline 1145
("preprint-with-id vs known published", _entry(*_both(venue='arXiv:2401.00001', web_venue='ICML')), 'MINOR'), ("url path case is significant", _entry(*_both(url='http://x/Method.pdf', web_url='http://x/method.pdf')), 'ESCALATE'), (" - Network accessline 1146
("url path case is significant", _entry(*_both(url='http://x/Method.pdf', web_url='http://x/method.pdf')), 'ESCALATE'), - Network accessline 1147
("diacritics in an id are significant", _entry(*_both(eprint='Resume', web_eprint='Résumé')), 'ESCALATE'), ("wrong url punctuation", _entry(*_both(url='https://arxiv.org/abs-2401/00001', web_u - Network accessline 1148
("wrong url punctuation", _entry(*_both(url='https://arxiv.org/abs-2401/00001', - Network accessline 1149
web_url='https://arxiv.org/abs/2401.00001')), 'ESCALATE'), - Network accessline 1310
_DOI_REC = "@article{k, title={T}, author={Smith, A}, year={2020}, journal={ICML}, doi={10.1/x}}" _MISC_URL_REC = "@misc{k, title={T}, author={Smith, A}, year={2020}, url={http://example.org/tr}}" - Network accessline 1311
_MISC_URL_REC = "@misc{k, title={T}, author={Smith, A}, year={2020}, url={http://example.org/tr}}" - Network accessline 1557
print('%d entr%s downgraded to ESCALATE for lack of a blindness attestation.' % (downgraded, 'y' if downgraded == 1 else 'ies')) print('ESCALATE entries REQUIRE the main agent\'s own primary-source fetch (Step 4).') - Network accessline 1558
% (downgraded, 'y' if downgraded == 1 else 'ies')) print('ESCALATE entries REQUIRE the main agent\'s own primary-source fetch (Step 4).') print('This gate recomputes the diff from A and B directly (C supplies only flags) and ' - Network accessline 1559
print('ESCALATE entries REQUIRE the main agent\'s own primary-source fetch (Step 4).')
skills/claims-drafting/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review,
skills/comm-lit-review/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write, mcp__zotero__*, mcp__obsidian-vault__*
skills/deepxiv/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 51
Authentication is handled by the third-party `deepxiv-sdk` CLI using `DEEPXIV_TOKEN`. In [SDK 1.2.2](https://pypi.org/project/deepxiv-sdk/1.2.2/), - Network accessline 52
`DEEPXIV_TOKEN`. In [SDK 1.2.2](https://pypi.org/project/deepxiv-sdk/1.2.2/), - Access to secretsline 55
[Credential-related source omitted]
skills/dse-loop/SKILL.md
skills/embodiment-description/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob
skills/exa-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 38
> - `/exa-search "transformer" — content: summary` — LLM-generated summaries > - `/exa-search "transformer" — domains: arxiv.org,huggingface.co` — domain filter > - `/exa-search "https://arxiv.org/abs/2301.07041" — similar` — find similar p - Network accessline 40
> - `/exa-search "https://arxiv.org/abs/2301.07041" — similar` — find similar pages - Access to secretsline 52
[Credential-related source omitted] - Network accessline 55
Get a key from [exa.ai](https://exa.ai). - Access to secretsline 201
[Credential-related source omitted]
skills/experiment-audit/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok
skills/experiment-bridge/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-r - Network accessline 43
> Override: `/experiment-bridge "EXPERIMENT_PLAN.md" — compact: true, base repo: https://github.com/org/project` - Network accessline 376
- **Budget awareness.** Track GPU-hours against the plan's budget. Warn if approaching the limit. - **Vast.ai lifecycle.** If using vast.ai instances, destroy them after all experiments complete and results are downloaded. Running instances - Network accessline 378
- **Modal lifecycle.** If using `gpu: modal`, no cleanup is needed — Modal auto-scales to zero after each run. But always show cost estimates before running and verify the spending limit is set at https://modal.com/settings (NEVER through C
skills/experiment-plan/SKILL.md
skills/experiment-queue/SKILL.md
skills/experiment-queue/scripts/build_manifest.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/experiment-queue/scripts/queue_manager.py
skills/feishu-notify/SKILL.md
- Broad permissionsline 1
Bash(curl *), Bash(cat *), Read, Glob - Network accessline 3
description: "Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says \"发飞书\", \"notify feishu\", or other skills need to send status updates." argument-hint: "[message-te - Network accessline 4
argument-hint: "[message-text]" allowed-tools: Bash(curl *), Bash(cat *), Read, Glob --- - Network accessline 5
allowed-tools: Bash(curl *), Bash(cat *), Read, Glob - Network accessline 25
{ "mode": "push", "webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/YOUR_WEBHOOK_ID", - Network accessline 26
"mode": "push", "webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/YOUR_WEBHOOK_ID", "interactive": { - Network accessline 27
"webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/YOUR_WEBHOOK_ID", - Network accessline 28
"interactive": { "bridge_url": "http://localhost:5000", "timeout_seconds": 300 - Network accessline 29
"bridge_url": "http://localhost:5000", - Network accessline 39
| **Off** | `"off"` or file absent | Nothing. Pure CLI as-is | Nothing | | **Push only** | `"push"` | Send webhook notifications at key events. Mobile push, no reply | Feishu bot webhook URL | | **Interactive** | `"interactive"` | Full bidi - Network accessline 41
| **Interactive** | `"interactive"` | Full bidirectional. Approve/reject from Feishu, reply to checkpoints | [feishu-claude-code](https://github.com/joewongjc/feishu-claude-code) running | - Network accessline 61
curl -s -X POST "$WEBHOOK_URL" \ - Network accessline 92
Interactive mode uses [feishu-claude-code](https://github.com/joewongjc/feishu-claude-code) as a bridge: - Network accessline 96
curl -s -X POST "$BRIDGE_URL/send" \ - Network accessline 103
curl -s "$BRIDGE_URL/poll?timeout=$TIMEOUT_SECONDS" - Network accessline 113
- **Push mode**: Check curl exit code. If non-zero, log warning but do NOT block the workflow.
skills/figure-description/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch
skills/figure-spec/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__rev
skills/figure-spec/scripts/figure_renderer.py
- Executable scriptline 1
#!/usr/bin/env python3 - Possible obfuscationline 78
val = re.sub(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f]", "", val) - Network accessline 349
svg = Element("svg", { "xmlns": "http://www.w3.org/2000/svg", - Network accessline 350
"xmlns": "http://www.w3.org/2000/svg", - Access to secretsline 653
[Credential-related source omitted]
skills/firecrawl-search/SKILL.md
- Broad permissionsline 1
Bash(*) - Network accessline 40
> - `/firecrawl-search "diffusion transformers" — time: qdr:m` — past month (`qdr:h`, `qdr:d`, `qdr:w`, `qdr:m`, `qdr:y`) > - `/firecrawl-search "LLM agents" — domains: arxiv.org,openreview.net` — domain filter > - `/firecrawl-search "https - Network accessline 42
> - `/firecrawl-search "https://arxiv.org/abs/2211.17192"` — a bare URL is scraped instead of searched - Access to secretsline 49
[Credential-related source omitted] - Network accessline 52
Get a key from [firecrawl.dev](https://www.firecrawl.dev/app/api-keys). Requests without a key are limited to a small daily cap.
skills/gemini-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, mcp__gemini-cli__* - Network accessline 51
3. **gemini-mcp-tool** — MCP bridge for Claude Code ([jamubc/gemini-mcp-tool](https://github.com/jamubc/gemini-mcp-tool)) - Access to secretsline 92
[Credential-related source omitted] - Network accessline 98
- Free key from [Google AI Studio](https://aistudio.google.com/apikey)
skills/grant-proposal/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__ - Network accessline 246
- Otherwise invoke `/research-lit` for multi-source literature search (arXiv, Scholar, Zotero, local PDFs) - Search for **funded projects** in the same area via WebSearch: - KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - Network accessline 247
- Search for **funded projects** in the same area via WebSearch: - KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - NSF → NSF Award Search (https://www.nsf.gov/awardsearch/) - Network accessline 248
- KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - Network accessline 249
- NSF → NSF Award Search (https://www.nsf.gov/awardsearch/)
skills/idea-creator/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Grep, Glob, WebSearch, WebFetch, Agent(aris-fanout-leaf), Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply, mcp__antigravity__antigravity, mcp__antigravity
skills/idea-discovery-robot/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex, mcp__codex__codex-reply
skills/idea-discovery/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex, mcp__codex__codex-reply - Network accessline 49
> 💡 These are defaults. Override by telling the skill, e.g., `/idea-discovery "topic" — ref paper: https://arxiv.org/abs/2406.04329` or `/idea-discovery "topic" — compact: true`. - Network accessline 165
1. **If arXiv URL** (e.g., `https://arxiv.org/abs/2406.04329`): - Invoke `/arxiv "ARXIV_ID" — download` to fetch the PDF
skills/integrity-forensics/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Grep, Glob, mcp__codex__codex - Broad permissionsline 1
Bash(*), Read, Write, Grep, Glob, mcp__codex__codex - Broad permissionsline 1
Bash(*), Read, Write, Grep, Glob, mcp__codex__codex - Network accessline 12
> **What this is.** ARIS generates papers; [Anti-Autoresearch](https://github.com/wanshuiyin/Anti-Autoresearch) - Network accessline 12
> **What this is.** ARIS generates papers; [Anti-Autoresearch](https://github.com/wanshuiyin/Anti-Autoresearch) - Network accessline 12
> **What this is.** ARIS generates papers; [Anti-Autoresearch](https://github.com/wanshuiyin/Anti-Autoresearch) - Network accessline 27
- **ANTI_AR_REPO = `https://github.com/wanshuiyin/Anti-Autoresearch.git`** - Network accessline 27
- **ANTI_AR_REPO = `https://github.com/wanshuiyin/Anti-Autoresearch.git`** - Network accessline 27
- **ANTI_AR_REPO = `https://github.com/wanshuiyin/Anti-Autoresearch.git`** - Network accessline 54
mkdir -p "$HOME/.aris" if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" - Network accessline 54
mkdir -p "$HOME/.aris" if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" - Network accessline 54
mkdir -p "$HOME/.aris" if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" - Network accessline 55
if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" fi - Network accessline 55
if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" fi - Network accessline 55
if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" fi - Network accessline 56
git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" fi # fetch ONLY if the pin isn't already present — a cached, validated pin works offline - Network accessline 56
git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" fi # fetch ONLY if the pin isn't already present — a cached, validated pin works offline - Network accessline 56
git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" fi # fetch ONLY if the pin isn't already present — a cached, validated pin works offline
skills/interview-cheatsheet/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__rev - Network accessline 214
| **<Topic> 面试 Cheat Sheet** | [`<slug>_tutorial.md`](<slug>_tutorial.md) | [`<slug>_tutorial.html`](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/tutorials/<slug>_tutorial.html) | <one-line topic list> |
skills/invention-structuring/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude
skills/jurisdiction-format/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob
skills/keenable-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read - Access to secretsline 20
[Credential-related source omitted] - Network accessline 36
> - `/keenable-search "foundation models" — start date: 2025-01-01` (recent pages only) > - `/keenable-search "transformer" — max chars: 8000` (longer snippets) > - `/keenable-search "https://arxiv.org/abs/2209.00796" — fetch` (the page as - Network accessline 38
> - `/keenable-search "https://arxiv.org/abs/2209.00796" — fetch` (the page as markdown) - Access to secretsline 48
[Credential-related source omitted] - Network accessline 51
Create a key in the [Keenable console](https://app.keenable.ai/console). - Access to secretsline 147
[Credential-related source omitted] - Access to secretsline 150
[Credential-related source omitted]
skills/kill-argument/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude
skills/lean-formalize/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__c - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__c - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__c - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__c - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__c - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__c
skills/lean-formalize/references/lean-working-loop.md
- Network accessline 176
- [Horizon Lean search](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/lean/lean-search/SKILL.md), - Network accessline 177
[proof cycle](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/lean/lean-cycle/SKILL.md), - Network accessline 178
[repair](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/lean/lean-proof-repair/SKILL.md), - Network accessline 179
and [representation experiments](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/review/definition-quality/references/representation-experiments.md). - Network accessline 180
- Horizon acknowledges its selected MIT-licensed adaptations from [cameronfreer/lean4-skills](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/_sources/lean4-ski - Network accessline 181
[cameronfreer/lean4-skills](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/_sources/lean4-skills/PROVENANCE.md). - Network accessline 182
- [Argus mathematical execution](https://github.com/lbx154/Argus/blob/9cfe9129fd90511c3a1865844ec7dfda1b5d1008/argus/verticals/math/skills/engineer/math-research-execution.md) - Network accessline 183
and [planning](https://github.com/lbx154/Argus/blob/9cfe9129fd90511c3a1865844ec7dfda1b5d1008/argus/verticals/math/skills/planner/math-research-planning.md).
skills/lean-formalize/references/verification-and-handoff.md
- Network accessline 74
steps with suitable proof-producing or kernel-reduced verification. If the task permits a different basis, disclose it accurately. General guidance is in the [Lean reference](https://lean-lang.org/doc/reference/latest/) and the community's - Network accessline 75
permits a different basis, disclose it accurately. General guidance is in the [Lean reference](https://lean-lang.org/doc/reference/latest/) and the community's [native computation discussion](https://leanprover-community.github.io/extras/pi - Network accessline 76
[Lean reference](https://lean-lang.org/doc/reference/latest/) and the community's - Network accessline 77
[native computation discussion](https://leanprover-community.github.io/extras/pitfalls.html#native_decide).
skills/mermaid-diagram/SKILL.md
skills/meta-apply/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__ - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__
skills/meta-optimize/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, - Broad permissionsline 1
Bash(*), Read, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, - Network accessline 439
Inspired by [Meta-Harness](https://arxiv.org/abs/2603.28052) (Lee et al., 2026) — end-to-end optimization of model harnesses via filesystem-based experience access and agentic code search. - Network accessline 439
Inspired by [Meta-Harness](https://arxiv.org/abs/2603.28052) (Lee et al., 2026) — end-to-end optimization of model harnesses via filesystem-based experience access and agentic code search.
skills/monitor-experiment/SKILL.md
- Network accessline 108
https://wandb.ai/<entity>/<project>/runs/<run_id>
skills/novelty-check/SKILL.md
- Broad permissionsline 1
Bash(*), WebSearch, WebFetch, Grep, Read, Glob, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp
skills/openalex/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted] - Network accessline 70
3. **Get API keys** (optional but recommended): - **OpenAlex API key**: Free tier $1/day (10,000 list calls, 1,000 search calls) from [openalex.org](https://openalex.org/) - Network accessline 71
- **OpenAlex API key**: Free tier $1/day (10,000 list calls, 1,000 search calls) from [openalex.org](https://openalex.org/)
skills/overleaf-sync/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Edit, Write, Skill - Access to secretsline 15
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted] - Network accessline 195
[Credential-related source omitted] - Access to secretsline 195
[Credential-related source omitted] - Access to secretsline 198
[Credential-related source omitted] - Network accessline 218
- `/citation-audit` — re-run after pulling Overleaf changes that add/edit `\cite{...}` - `/paper-compile` — local LaTeX build; Overleaf compiles independently in the cloud - Overleaf Git bridge docs: https://www.overleaf.com/learn/how-to/Us - Network accessline 220
- Overleaf Git bridge docs: https://www.overleaf.com/learn/how-to/Using_Git_and_GitHub
skills/paper-claim-audit/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp_
skills/paper-compile/SKILL.md
skills/paper-figure/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__ - Network accessline 302
- **No decorative elements** — no background colors, no 3D effects, no chart junk - **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if need - Network accessline 303
- **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - **One script per figure** — easy to re-run individual figures when data chang - Network accessline 304
- **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - Network accessline 325
Design pattern (type × style matrix) inspired by [baoyu-skills](https://github.com/jimliu/baoyu-skills). Publication style defaults and figure rules from [pedrohcgs/claude-code-my-workflow](https://github.com/pedrohcgs/claude-code-my-workfl
skills/paper-illustration-image2/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, mcp__codex-image2__generate, mcp__codex-image2__generate_start, mcp__codex-image2__generate_status, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravi
skills/paper-illustration-image2/scripts/paper_illustration_image2.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-illustration/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, WebSearch - Access to secretsline 73
[Credential-related source omitted] - Network accessline 206
[Credential-related source omitted] - Access to secretsline 206
[Credential-related source omitted] - Network accessline 207
[Credential-related source omitted] - Access to secretsline 207
[Credential-related source omitted] - Network accessline 208
echo "Get your key from: https://aistudio.google.com/app/apikey" - Access to secretsline 209
[Credential-related source omitted] - Network accessline 326
[Credential-related source omitted] - Access to secretsline 326
[Credential-related source omitted] - Network accessline 327
[Credential-related source omitted] - Access to secretsline 327
[Credential-related source omitted] - Network accessline 359
# Call Gemini gemini-3-pro-preview for layout optimization (DIRECT connection, no proxy) RESPONSE=$(curl -s --max-time 90 \ - Network accessline 360
RESPONSE=$(curl -s --max-time 90 \ - Network accessline 388
[Credential-related source omitted] - Access to secretsline 388
[Credential-related source omitted] - Network accessline 389
[Credential-related source omitted] - Access to secretsline 389
[Credential-related source omitted] - Network accessline 422
# Call Gemini gemini-3-pro-preview for style verification (DIRECT connection, no proxy) RESPONSE=$(curl -s --max-time 90 \ - Network accessline 423
RESPONSE=$(curl -s --max-time 90 \ - Network accessline 458
[Credential-related source omitted] - Access to secretsline 458
[Credential-related source omitted] - Network accessline 459
[Credential-related source omitted] - Access to secretsline 459
[Credential-related source omitted] - Network accessline 487
# Call Paperbanana API WITHOUT proxy (direct connection works better) RESPONSE=$(curl -s --max-time 180 \ - Network accessline 488
RESPONSE=$(curl -s --max-time 180 \ - Possible obfuscationline 516
img_data = base64.b64decode(part['inlineData']['data'])
skills/paper-plan/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__ - Network accessline 143
Original idea: @zhangpelf in [#217](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/217). - Network accessline 393
Outline methodology inspired by [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (claim-evidence mapping), [claude-scholar](https://github.com/Galaxy-Dawn/claude-scholar) (citation verification),
skills/paper-poster-html/NOTICE.md
- Network accessline 8
- **Upstream**: posterly — https://github.com/Chenruishuo/posterly
skills/paper-poster-html/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebFetch, WebSearch, AskUserQuestion, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__cl - Network accessline 22
via Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen preview lies; only print emulation at the correct viewport tells the truth. Core gate machinery is adapted from [posterly](https://github.com/Chenruishuo/ - Network accessline 23
preview lies; only print emulation at the correct viewport tells the truth. Core gate machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, © 2026 Ruishuo Chen — see `NOTICE.md` and `LICENSES/posterly-MIT.txt`) - Network accessline 24
machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, ©
skills/paper-poster-html/scripts/_posterly/__init__.py
- Executable scriptline 1
Executable file
skills/paper-poster-html/scripts/_posterly/canvas.py
- Executable scriptline 1
Executable file
skills/paper-poster-html/scripts/_posterly/measure.py
- Executable scriptline 1
Executable file
skills/paper-poster-html/scripts/_posterly/polish.py
- Executable scriptline 1
Executable file
skills/paper-poster-html/scripts/_posterly/preflight.py
- Executable scriptline 1
Executable file
skills/paper-poster-html/scripts/_posterly/render.py
- Executable scriptline 1
Executable file
skills/paper-poster-html/scripts/_posterly/textutil.py
- Executable scriptline 1
Executable file
skills/paper-poster-html/scripts/_posterly/verify_final.py
skills/paper-poster-html/scripts/asset_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-poster-html/scripts/extract_pdf_figures.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-poster-html/scripts/poster_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-poster-html/scripts/preprocess_figures.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-poster-html/scripts/render_preview.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-poster-html/scripts/run_gates.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-poster-html/scripts/style_check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/paper-poster-html/templates/landscape_4col.html
- Network accessline 52
}; </script> <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> - Network accessline 54
<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> - Network accessline 827
SVG placeholder so the template renders offline. Generate a real one with one of: $ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode - Network accessline 828
one of: $ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode $ python -c "import qrcode; qrcode.make('https://your-url').save('qr.png')" - Network accessline 829
$ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode - Network accessline 830
$ python -c "import qrcode; qrcode.make('https://your-url').save('qr.png')" - Network accessline 832
The placeholder data-URI carries data-color-exempt="logo" so its literal fills are exempt from the color gate. --> <img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewB - Network accessline 833
literal fills are exempt from the color gate. --> <img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill='%23fff'/><g fill='%23222 - Network accessline 834
<img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill='%23fff'/><g fill='%23222'><rect x='4' y='4' width='26' height='26'/><rect x='70' y
skills/paper-poster-html/templates/landscape_hero.html
- Network accessline 69
}; </script> <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> - Network accessline 71
<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> - Network accessline 895
monochrome black/white SVG (data-color-exempt="logo" marks it as a non-palette graphic for style_check). Generate a real one with: $ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode - Network accessline 896
non-palette graphic for style_check). Generate a real one with: $ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode $ python -c "import qrcode; qrcode.make('https://your-url').save('qr - Network accessline 897
$ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode - Network accessline 898
$ python -c "import qrcode; qrcode.make('https://your-url').save('qr.png')" - Network accessline 899
then change src to "assets/qr/qr.png" (export at >= 2x rendered size). --> <img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill= - Network accessline 900
<img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill='%23fff'/><g fill='%23222'><rect x='4' y='4' width='26' height='26'/><rect x='70' y
skills/paper-poster-html/templates/portrait_2col.html
- Network accessline 62
}; </script> <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> - Network accessline 64
<script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-svg.js"></script> - Network accessline 760
monochrome black/white SVG (data-color-exempt="logo" marks it as a non-palette graphic for style_check). Generate a real one with: $ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode - Network accessline 761
non-palette graphic for style_check). Generate a real one with: $ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode $ python -c "import qrcode; qrcode.make('https://your-url').save('qr - Network accessline 762
$ qrencode -o qr.png -s 12 -m 0 "https://your-url" # apt install qrencode - Network accessline 763
$ python -c "import qrcode; qrcode.make('https://your-url').save('qr.png')" - Network accessline 764
then change src to "assets/qr/qr.png" (export at >= 2x rendered size). --> <img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill= - Network accessline 765
<img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill='%23fff'/><g fill='%23222'><rect x='4' y='4' width='26' height='26'/><rect x='70' y
skills/paper-slides/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__
skills/paper-talk/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex
skills/paper-write/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, - Network accessline 115
Original idea: @zhangpelf in [#217](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/issues/217). - Network accessline 334
#### Verified BibTeX Fetch (when DBLP_BIBTEX = true) - Network accessline 340
# 1. Search by title + first author curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 341
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 342
# 2. Extract DBLP key from result (e.g., conf/nips/VaswaniSPUJGKP17) # 3. Fetch real BibTeX curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 344
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 349
# If paper has a DOI or arXiv ID (arXiv DOI = 10.48550/arXiv.{id}) curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 350
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 405
def dblp_hits(title): q = urllib.parse.quote(title) url = f"https://dblp.org/search/publ/api?q={q}&format=json&h=3" - Network accessline 406
q = urllib.parse.quote(title) url = f"https://dblp.org/search/publ/api?q={q}&format=json&h=3" with urllib.request.urlopen(url, timeout=20) as r: - Network accessline 407
url = f"https://dblp.org/search/publ/api?q={q}&format=json&h=3" with urllib.request.urlopen(url, timeout=20) as r: data = json.load(r) - Network accessline 408
with urllib.request.urlopen(url, timeout=20) as r: - Network accessline 412
def crossref_entry(doi): req = urllib.request.Request(f"https://doi.org/{doi}", headers={"Accept": "application/x-bibtex"}) - Network accessline 413
req = urllib.request.Request(f"https://doi.org/{doi}", headers={"Accept": "application/x-bibtex"}) - Network accessline 414
with urllib.request.urlopen(req, timeout=20) as r: - Network accessline 698
Writing methodology adapted from [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (CCF award-winning methodology). Citation verification from [claude-scholar](https://github.com/Galaxy-Dawn/claude
skills/paper-write/templates/IEEEtran.bst
- Network accessline 14
%% %% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 15
%% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ %% http://www.ctan.org/pkg/ieeetran - Network accessline 16
%% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 17
%% http://www.ctan.org/pkg/ieeetran - Network accessline 18
%% and/or %% http://www.ieee.org/ %% - Network accessline 19
%% http://www.ieee.org/ - Network accessline 38
%% %% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 39
%% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, %% distributed and modified. A copy of the LPPL, version 1.3, is included - Network accessline 40
%% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 157
FUNCTION{bst.file.version} { "1.14" } FUNCTION{bst.file.date} { "2015/08/26" } FUNCTION{bst.file.website} { "http://www.michaelshell.org/tex/ieeetran/bibtex/" } - Network accessline 159
FUNCTION{bst.file.website} { "http://www.michaelshell.org/tex/ieeetran/bibtex/" }
skills/paper-write/templates/IEEEtran.cls
- Network accessline 7
%% %% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 8
%% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ %% http://www.ctan.org/pkg/ieeetran - Network accessline 9
%% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 10
%% http://www.ctan.org/pkg/ieeetran - Network accessline 11
%% and %% http://www.ieee.org/ %% - Network accessline 12
%% http://www.ieee.org/ - Network accessline 30
%% Current maintainer (V1.3 to V1.8b): Michael Shell %% See: %% http://www.michaelshell.org/ - Network accessline 31
%% See: %% http://www.michaelshell.org/ %% for current contact information. - Network accessline 32
%% http://www.michaelshell.org/ - Network accessline 52
%% %% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 53
%% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, %% distributed and modified. A copy of the LPPL, version 1.3, is included - Network accessline 54
%% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 138
% the corresponding dvips paper name is "ieeecs". % See the testflow documentation % http://www.ctan.org/tex-archive/macros/latex/contrib/IEEEtran/testflow - Network accessline 139
% See the testflow documentation % http://www.ctan.org/tex-archive/macros/latex/contrib/IEEEtran/testflow % for more details on dvips paper size configuration. - Network accessline 140
% http://www.ctan.org/tex-archive/macros/latex/contrib/IEEEtran/testflow - Network accessline 206
\ProvidesClass{IEEEtran}[2015/08/26 V1.8b by Michael Shell] \typeout{-- See the "IEEEtran_HOWTO" manual for usage information.} \typeout{-- http://www.michaelshell.org/tex/ieeetran/} - Network accessline 207
\typeout{-- See the "IEEEtran_HOWTO" manual for usage information.} \typeout{-- http://www.michaelshell.org/tex/ieeetran/} \NeedsTeXFormat{LaTeX2e} - Network accessline 208
\typeout{-- http://www.michaelshell.org/tex/ieeetran/}
skills/paper-write/templates/iclr2026.tex
skills/paper-write/templates/icml2025.tex
skills/paper-write/templates/neurips2025.tex
skills/paper-writing/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-r - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 333
[Credential-related source omitted] - Access to secretsline 349
[Credential-related source omitted] - Access to secretsline 358
[Credential-related source omitted]
skills/patent-novelty-check/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__revi
skills/patent-pipeline/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex
skills/patent-review/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__
skills/pixel-art/SKILL.md
- Network accessline 63
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 W H" font-family="monospace">
skills/prior-art-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write
skills/proof-checker/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, Agent(aris-fanout-leaf), mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply, Skill(lean-formalize), mcp__antigravity__antigravity, mcp__antigravit
skills/proof-orchestrator/NOTICE.md
- Network accessline 5
Upstream: <https://github.com/shenmuxing/EtaSkill> (licensed MPL-2.0 as a
skills/qzcli/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 12
**GitHub:** [tianyilt/qzcli_tool](https://github.com/tianyilt/qzcli_tool) - Network accessline 25
pip install rich requests prompt_toolkit mcp git clone https://github.com/tianyilt/qzcli_tool - Network accessline 26
git clone https://github.com/tianyilt/qzcli_tool - Access to secretsline 52
[Credential-related source omitted] - Network accessline 58
[Credential-related source omitted] - Network accessline 60
export QZCLI_API_URL="https://qz.yourorg.edu.cn"
skills/rebuttal/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, Skill, mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mc
skills/render-html/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_st - Network accessline 317
For deck / poster / Xiaohongshu card / tweet card / data report style outputs, point users to **[html-anything](https://github.com/nexu-io/html-anything)** (Apache-2.0, 3000⭐ at time of writing). It ships 75 SKILL.md templates across 9 surf
skills/render-html/scripts/render_html.py
- Executable scriptline 1
#!/usr/bin/env python3 - Possible obfuscationline 247
(re.compile(r"^[⚠<U+FE0F>⚠]<U+FE0F>?\s*"), "callout-warn", "Warning"), - Possible obfuscationline 729
md = md.lstrip("<U+FEFF>") - Network accessline 754
}; </script> <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js" async></script> - Network accessline 756
<script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js" async></script> - Network accessline 758
<!-- highlight.js --> <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@11.9.0/build/styles/atom-one-light.min.css"> - Network accessline 759
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@11.9.0/build/styles/atom-one-light.min.css"> - Network accessline 760
<script src="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@11.9.0/build/highlight.min.js"></script>
skills/render-html/scripts/templates/academic.html
- Network accessline 484
<footer class="aris-footer"> Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> · - Network accessline 485
Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> · - Network accessline 649
(info.key ? '<div class="cp-key">' + escapeHtml(info.key) + '</div>' : '') + (info.arxiv ? '<a class="cp-link" href="https://arxiv.org/abs/' + encodeURIComponent(info.arxiv) + - Network accessline 650
(info.arxiv ? '<a class="cp-link" href="https://arxiv.org/abs/' + encodeURIComponent(info.arxiv) + '" target="_blank" rel="noopener">arXiv ' + escapeHtml(info.arxiv) + ' ↗</a>' - Network accessline 651
? '<a class="cp-link" href="https://arxiv.org/abs/' + encodeURIComponent(info.arxiv) +
skills/render-html/scripts/templates/dashboard.html
- Network accessline 323
<footer class="aris-footer"> Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> · - Network accessline 324
Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> ·
skills/research-implement-feature/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, AskUserQuestion, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__revi
skills/research-lit/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write, Agent(aris-fanout-leaf), mcp__zotero__*, mcp__obsidian-vault__*
skills/research-pipeline/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex, mcp__codex__codex-reply - Network accessline 70
> 💡 Override via argument, e.g., `/research-pipeline "topic" — AUTO_PROCEED: false, human checkpoint: true, difficulty: nightmare, code review: false, base repo: https://github.com/org/project, auto_write: true, venue: NeurIPS`.
skills/research-refine-pipeline/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply
skills/research-refine/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review,
skills/research-review/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply, mcp__manual_review__review, mcp__manual_review__review_reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok
skills/research-wiki/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply - Network accessline 16
Inspired by [Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): compile knowledge once, keep it current, don't re-derive on every query. - Network accessline 16
Inspired by [Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): compile knowledge once, keep it current, don't re-derive on every query. - Network accessline 462
Inspired by [Karpathy's LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) — "compile knowledge once, keep it current, don't re-derive on every query." - Network accessline 462
Inspired by [Karpathy's LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) — "compile knowledge once, keep it current, don't re-derive on every query."
skills/resubmit-pipeline/SKILL.md
skills/result-to-claim/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__
skills/run-experiment/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Edit, Write, Skill(serverless-modal) - Access to secretsline 149
[Credential-related source omitted] - Access to secretsline 160
[Credential-related source omitted] - Access to secretsline 162
[Credential-related source omitted] - Dangerous shell operationline 285
- Conda: `eval "$(/opt/conda/bin/conda shell.bash hook)" && conda activate research` - Network accessline 309
> **Vast.ai setup**: Run `pip install vastai && vastai set api-key YOUR_KEY`. Upload your SSH public key at https://cloud.vast.ai/manage-keys/. Set `gpu: vast` in your `CLAUDE.md` — `/run-experiment` will automatically rent an instance, run - Network accessline 311
> **Modal setup**: Run `pip install modal && modal setup`. Bind a payment method at https://modal.com/settings (NEVER through CLI) to unlock the full $30/month free tier (without card: $5/month only). Set a workspace spending limit to preve - Network accessline 313
[Credential-related source omitted] - Access to secretsline 313
[Credential-related source omitted]
skills/semantic-scholar/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 101
If `$S2_FETCHER` is empty (Policy D1 cascade), fall back to inline Python using `urllib` against `https://api.semanticscholar.org/graph/v1/paper/search`. - Network accessline 144
For each paper, also show: - **DOI link**: `https://doi.org/DOI` (for IEEE/ACM papers, this is the canonical link) - Network accessline 145
- **DOI link**: `https://doi.org/DOI` (for IEEE/ACM papers, this is the canonical link) - Network accessline 231
- **Venue metadata matters**: Show `venue` and `publicationVenue.type` (journal vs conference) — this helps users assess paper quality. - **DOI is the canonical ID for published papers**: Always show DOI links for IEEE/ACM/Springer papers. - Network accessline 232
- **DOI is the canonical ID for published papers**: Always show DOI links for IEEE/ACM/Springer papers. - **Rate limiting**: S2 API without key is heavily rate-limited (~1 req/s, strict cooldown). If HTTP 429 occurs, wait and retry. Recomme - Network accessline 233
[Credential-related source omitted] - Access to secretsline 233
[Credential-related source omitted]
skills/serverless-modal/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Edit, Write - Network accessline 37
- Sign up: https://modal.com (GitHub/Google login) - Network accessline 38
- Free (no card): **$5/month** — enough for quick tests - Free (with card): **$30/month** — bind a payment method at https://modal.com/settings for the full free tier. Set a **workspace spending limit** to prevent accidental overcharge (Set - Network accessline 39
- Free (with card): **$30/month** — bind a payment method at https://modal.com/settings for the full free tier. Set a **workspace spending limit** to prevent accidental overcharge (Settings → Usage → Spending Limit) - Network accessline 43
> **Recommended setup**: Bind a card to unlock $30/month, then immediately set a spending limit (e.g., $30) so you never exceed the free tier. Modal will pause your workloads when the limit is hit. > > **SECURITY WARNING**: Always bind your - Network accessline 45
> **SECURITY WARNING**: Always bind your card and set spending limits directly on https://modal.com/settings in your browser. NEVER enter payment information, card numbers, or billing details through Claude Code or any CLI tool. Only the of - Dangerous shell operationline 278
modal volume rm <volume-name> # Delete a volume when done - Network accessline 328
> **Cost protection**: After `modal setup`, go to https://modal.com/settings in your browser (NEVER through CLI) → bind a payment method to unlock $30/month free tier (without card: only $5/month). Then set a **workspace spending limit** eq - Network accessline 332
- Docs: https://modal.com/docs/guide - Network accessline 333
- GPU: https://modal.com/docs/guide/gpu - Network accessline 334
- Pricing: https://modal.com/pricing - Network accessline 335
- Examples: https://modal.com/docs/examples
skills/shared-references/citation-discipline.md
- Network accessline 283
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 283
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 283
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 283
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 283
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 284
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 284
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 284
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 284
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 284
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 290
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 290
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 290
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 290
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 290
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}"
skills/shared-references/injection-hygiene.md
skills/shared-references/integration-contract.md
- Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 342
| `forensics_gate.py` (in `/integrity-forensics`, `/paper-writing` Phase 5.9/6.0, `/resubmit-pipeline`) | A (gate) | Typed policy gate + append-only obligations ledger for the Anti-Autoresearch launcher; at `assurance: submission` an unreso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso - Network accessline 344
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): it assigns every `MATCH`/`MINOR` that is granted without a fetch (Step 4 may still reso
skills/shared-references/prior-art-databases.md
- Access to secretsline 56
[Credential-related source omitted]
skills/shared-references/reviewer-routing.md
- Network accessline 166
[Credential-related source omitted] - Network accessline 166
[Credential-related source omitted] - Network accessline 166
[Credential-related source omitted] - Network accessline 166
[Credential-related source omitted] - Network accessline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Network accessline 167
[Credential-related source omitted] - Network accessline 167
[Credential-related source omitted] - Network accessline 167
[Credential-related source omitted] - Network accessline 167
[Credential-related source omitted] - Network accessline 167
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Network accessline 168
--env LLM_BASE_URL=https://example.com/v1 \ - Network accessline 168
--env LLM_BASE_URL=https://example.com/v1 \ - Network accessline 168
--env LLM_BASE_URL=https://example.com/v1 \ - Network accessline 168
--env LLM_BASE_URL=https://example.com/v1 \ - Network accessline 168
--env LLM_BASE_URL=https://example.com/v1 \ - Access to secretsline 212
[Credential-related source omitted] - Access to secretsline 212
[Credential-related source omitted] - Access to secretsline 212
[Credential-related source omitted] - Access to secretsline 212
[Credential-related source omitted] - Access to secretsline 212
[Credential-related source omitted] - Access to secretsline 264
[Credential-related source omitted] - Access to secretsline 264
[Credential-related source omitted] - Access to secretsline 264
[Credential-related source omitted] - Access to secretsline 264
[Credential-related source omitted] - Access to secretsline 264
[Credential-related source omitted] - Network accessline 276
Oracle MCP is maintained at [`steipete/oracle`](https://github.com/steipete/oracle). When you invoke `— reviewer: oracle-pro` (and especially the `o3-deep-research` / `gpt-5.5-pro` paths), it's worth checking the **[open PRs](https://github - Network accessline 276
Oracle MCP is maintained at [`steipete/oracle`](https://github.com/steipete/oracle). When you invoke `— reviewer: oracle-pro` (and especially the `o3-deep-research` / `gpt-5.5-pro` paths), it's worth checking the **[open PRs](https://github - Network accessline 276
Oracle MCP is maintained at [`steipete/oracle`](https://github.com/steipete/oracle). When you invoke `— reviewer: oracle-pro` (and especially the `o3-deep-research` / `gpt-5.5-pro` paths), it's worth checking the **[open PRs](https://github - Network accessline 276
Oracle MCP is maintained at [`steipete/oracle`](https://github.com/steipete/oracle). When you invoke `— reviewer: oracle-pro` (and especially the `o3-deep-research` / `gpt-5.5-pro` paths), it's worth checking the **[open PRs](https://github - Network accessline 276
Oracle MCP is maintained at [`steipete/oracle`](https://github.com/steipete/oracle). When you invoke `— reviewer: oracle-pro` (and especially the `o3-deep-research` / `gpt-5.5-pro` paths), it's worth checking the **[open PRs](https://github - Network accessline 305
When the resolved selection is `agy`, route the review through the **gemini-review MCP** with the Antigravity (`agy`) backend — a native cross-model reviewer for Antigravity users who don't run Codex MCP / Oracle. Added in [#267](https://gi - Network accessline 305
When the resolved selection is `agy`, route the review through the **gemini-review MCP** with the Antigravity (`agy`) backend — a native cross-model reviewer for Antigravity users who don't run Codex MCP / Oracle. Added in [#267](https://gi - Network accessline 305
When the resolved selection is `agy`, route the review through the **gemini-review MCP** with the Antigravity (`agy`) backend — a native cross-model reviewer for Antigravity users who don't run Codex MCP / Oracle. Added in [#267](https://gi - Network accessline 305
When the resolved selection is `agy`, route the review through the **gemini-review MCP** with the Antigravity (`agy`) backend — a native cross-model reviewer for Antigravity users who don't run Codex MCP / Oracle. Added in [#267](https://gi - Network accessline 305
When the resolved selection is `agy`, route the review through the **gemini-review MCP** with the Antigravity (`agy`) backend — a native cross-model reviewer for Antigravity users who don't run Codex MCP / Oracle. Added in [#267](https://gi - Dangerous shell operationline 771
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 771
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 771
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 771
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 771
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 809
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 809
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 809
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 809
trap 'rm -f "$PROMPTFILE"' EXIT - Dangerous shell operationline 809
trap 'rm -f "$PROMPTFILE"' EXIT
skills/skills-codex-claude-review/paper-figure/SKILL.md
- Network accessline 296
- **No decorative elements** — no background colors, no 3D effects, no chart junk - **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if need - Network accessline 297
- **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - **One script per figure** — easy to re-run individual figures when data chang - Network accessline 298
- **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - Network accessline 319
Design pattern (type × style matrix) inspired by [baoyu-skills](https://github.com/jimliu/baoyu-skills). Publication style defaults and figure rules from [pedrohcgs/claude-code-my-workflow](https://github.com/pedrohcgs/claude-code-my-workfl
skills/skills-codex-claude-review/paper-plan/SKILL.md
- Network accessline 280
Outline methodology inspired by [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (claim-evidence mapping), [claude-scholar](https://github.com/Galaxy-Dawn/claude-scholar) (citation verification),
skills/skills-codex-claude-review/paper-write/SKILL.md
- Network accessline 245
#### Verified BibTeX Fetch (when DBLP_BIBTEX = true) - Network accessline 251
# 1. Search by title + first author curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 252
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 253
# 2. Extract DBLP key from result (e.g., conf/nips/VaswaniSPUJGKP17) # 3. Fetch real BibTeX curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 255
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 260
# If paper has a DOI or arXiv ID (arXiv DOI = 10.48550/arXiv.{id}) curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 261
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 481
Principles from [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills): - Network accessline 488
De-AI patterns from [kgraph57/paper-writer-skill](https://github.com/kgraph57/paper-writer-skill): - Network accessline 496
Writing methodology adapted from [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (CCF award-winning methodology). Citation verification from [claude-scholar](https://github.com/Galaxy-Dawn/claude
skills/skills-codex-gemini-review/grant-proposal/SKILL.md
- Network accessline 193
- Otherwise invoke `/research-lit` for multi-source literature search (arXiv, Scholar, Zotero, local PDFs) - Search for **funded projects** in the same area via WebSearch: - KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - Network accessline 194
- Search for **funded projects** in the same area via WebSearch: - KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - NSF → NSF Award Search (https://www.nsf.gov/awardsearch/) - Network accessline 195
- KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - Network accessline 196
- NSF → NSF Award Search (https://www.nsf.gov/awardsearch/)
skills/skills-codex-gemini-review/paper-figure/SKILL.md
- Network accessline 266
- **No decorative elements** — no background colors, no 3D effects, no chart junk - **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if need - Network accessline 267
- **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - **One script per figure** — easy to re-run individual figures when data chang - Network accessline 268
- **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - Network accessline 289
Design pattern (type × style matrix) inspired by [baoyu-skills](https://github.com/jimliu/baoyu-skills). Publication style defaults and figure rules from [pedrohcgs/claude-code-my-workflow](https://github.com/pedrohcgs/claude-code-my-workfl
skills/skills-codex-gemini-review/paper-plan/SKILL.md
- Network accessline 265
Outline methodology inspired by [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (claim-evidence mapping), [claude-scholar](https://github.com/Galaxy-Dawn/claude-scholar) (citation verification),
skills/skills-codex-gemini-review/paper-poster-html/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__gemini-review__review, mcp__gemini-review__review_start, mcp__gemini-review__review_reply_start, mcp__gemini-review__review_status - Network accessline 15
via Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen preview lies; only print emulation at the correct viewport tells the truth. Core gate machinery is adapted from [posterly](https://github.com/Chenruishuo/ - Network accessline 16
preview lies; only print emulation at the correct viewport tells the truth. Core gate machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, © 2026 Ruishuo Chen — see `NOTICE.md` and `LICENSES/posterly-MIT.txt` - Network accessline 17
machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, ©
skills/skills-codex-gemini-review/paper-slides/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__gemini-review__review, mcp__gemini-review__review_start, mcp__gemini-review__review_reply_start, mcp__gemini-review__review_status
skills/skills-codex-gemini-review/paper-write/SKILL.md
- Network accessline 193
#### Verified BibTeX Fetch (when DBLP_BIBTEX = true) - Network accessline 199
# 1. Search by title + first author curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 200
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 201
# 2. Extract DBLP key from result (e.g., conf/nips/VaswaniSPUJGKP17) # 3. Fetch real BibTeX curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 203
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 208
# If paper has a DOI or arXiv ID (arXiv DOI = 10.48550/arXiv.{id}) curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 209
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 407
Principles from [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills): - Network accessline 414
De-AI patterns from [kgraph57/paper-writer-skill](https://github.com/kgraph57/paper-writer-skill): - Network accessline 422
Writing methodology adapted from [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (CCF award-winning methodology). Citation verification from [claude-scholar](https://github.com/Galaxy-Dawn/claude
skills/skills-codex-gemini-review/paper-writing/SKILL.md
- Access to secretsline 110
[Credential-related source omitted]
skills/skills-codex/ablation-planner/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit
skills/skills-codex/alphaxiv/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Glob - Network accessline 12
> Quick single-paper reader with tiered source fallback (overview → full markdown → LaTeX source). Powered by [AlphaXiv](https://www.alphaxiv.org). - Network accessline 29
- **OVERVIEW_URL** = `https://www.alphaxiv.org/overview/{PAPER_ID}.md` - Network accessline 30
- **ABS_URL** = `https://www.alphaxiv.org/abs/{PAPER_ID}.md` - Network accessline 31
- **ARXIV_SRC_URL** = `https://arxiv.org/src/{PAPER_ID}` - Network accessline 34
> Overrides (append to arguments): > - `/alphaxiv 2401.12345` — quick overview > - `/alphaxiv "https://arxiv.org/abs/2401.12345"` — auto-extract ID - Network accessline 35
> - `/alphaxiv 2401.12345` — quick overview > - `/alphaxiv "https://arxiv.org/abs/2401.12345"` — auto-extract ID > - `/alphaxiv 2401.12345 - depth: src` — force LaTeX source inspection - Network accessline 36
> - `/alphaxiv "https://arxiv.org/abs/2401.12345"` — auto-extract ID - Network accessline 46
- `https://arxiv.org/abs/2401.12345` or `https://arxiv.org/abs/2401.12345v2` - Network accessline 47
- `https://arxiv.org/pdf/2401.12345` - Network accessline 48
- `https://alphaxiv.org/overview/2401.12345` or `https://www.alphaxiv.org/overview/2401.12345` - Network accessline 49
- `https://alphaxiv.org/abs/2401.12345` or `https://www.alphaxiv.org/abs/2401.12345` - Network accessline 62
curl -sL --max-time 15 -A "{ALPHAXIV_UA}" "https://www.alphaxiv.org/overview/{PAPER_ID}.md" - Network accessline 76
curl -sL --max-time 15 -A "{ALPHAXIV_UA}" "https://www.alphaxiv.org/abs/{PAPER_ID}.md" - Network accessline 88
When the overview and full markdown are both insufficient (e.g., the user asks about equations, proofs, appendix details, or implementation specifics), download the paper's LaTeX source from `https://arxiv.org/src/{PAPER_ID}`. - Network accessline 109
- **arXiv**: [PAPER_ID] — https://arxiv.org/abs/[PAPER_ID]
skills/skills-codex/arxiv/SKILL.md
- Network accessline 69
NS = "http://www.w3.org/2005/Atom" query = urllib.parse.quote("QUERY") - Network accessline 70
query = urllib.parse.quote("QUERY") url = (f"http://export.arxiv.org/api/query" f"?search_query={query}&start=0&max_results=MAX_RESULTS" - Network accessline 71
url = (f"http://export.arxiv.org/api/query" - Network accessline 72
f"?search_query={query}&start=0&max_results=MAX_RESULTS" f"&sortBy=relevance&sortOrder=descending") with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 73
f"&sortBy=relevance&sortOrder=descending") with urllib.request.urlopen(url, timeout=30) as r: root = ET.fromstring(r.read()) - Network accessline 74
with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 89
"published": published, "categories": cats, "pdf_url": f"https://arxiv.org/pdf/{aid}.pdf", - Network accessline 90
"categories": cats, "pdf_url": f"https://arxiv.org/pdf/{aid}.pdf", "abs_url": f"https://arxiv.org/abs/{aid}", - Network accessline 91
"pdf_url": f"https://arxiv.org/pdf/{aid}.pdf", - Network accessline 92
"abs_url": f"https://arxiv.org/abs/{aid}", - Network accessline 113
python3 -c " import urllib.request, xml.etree.ElementTree as ET NS = 'http://www.w3.org/2005/Atom' - Network accessline 114
import urllib.request, xml.etree.ElementTree as ET NS = 'http://www.w3.org/2005/Atom' url = 'http://export.arxiv.org/api/query?id_list=ARXIV_ID' - Network accessline 115
NS = 'http://www.w3.org/2005/Atom' url = 'http://export.arxiv.org/api/query?id_list=ARXIV_ID' with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 116
url = 'http://export.arxiv.org/api/query?id_list=ARXIV_ID' with urllib.request.urlopen(url, timeout=30) as r: root = ET.fromstring(r.read()) - Network accessline 117
with urllib.request.urlopen(url, timeout=30) as r: - Network accessline 141
print(f'Already exists: {out}') sys.exit(0) req = urllib.request.Request( - Network accessline 142
sys.exit(0) req = urllib.request.Request( 'https://arxiv.org/pdf/ARXIV_ID.pdf', - Network accessline 143
req = urllib.request.Request( - Network accessline 144
'https://arxiv.org/pdf/ARXIV_ID.pdf', - Network accessline 145
headers={'User-Agent': 'arxiv-skill/1.0'}, ) with urllib.request.urlopen(req, timeout=60) as r: - Network accessline 146
) with urllib.request.urlopen(req, timeout=60) as r: out.write_bytes(r.read()) - Network accessline 147
with urllib.request.urlopen(req, timeout=60) as r:
skills/skills-codex/auto-paper-improvement-loop/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/auto-review-loop-llm/SKILL.md
- Network accessline 32
[Credential-related source omitted] - Network accessline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Network accessline 34
"LLM_BASE_URL": "https://api.deepseek.com/v1", - Network accessline 44
| Provider | LLM_BASE_URL | LLM_MODEL | |----------|--------------|-----------| | **OpenAI** | `https://api.openai.com/v1` | `gpt-6.1-sol`, `gpt-6-astra` | - Network accessline 45
|----------|--------------|-----------| | **OpenAI** | `https://api.openai.com/v1` | `gpt-6.1-sol`, `gpt-6-astra` | | **DeepSeek** | `https://api.deepseek.com/v1` | `deepseek-chat`, `deepseek-reasoner` | - Network accessline 46
| **OpenAI** | `https://api.openai.com/v1` | `gpt-6.1-sol`, `gpt-6-astra` | - Network accessline 47
| **DeepSeek** | `https://api.deepseek.com/v1` | `deepseek-chat`, `deepseek-reasoner` | - Network accessline 48
| **MiniMax** | `https://api.minimax.io/v1` | `MiniMax-M3` | - Network accessline 49
| **Kimi (Moonshot)** | `https://api.moonshot.cn/v1` | `moonshot-v1-8k`, `moonshot-v1-32k` | - Network accessline 50
| **ZhiPu (GLM)** | `https://open.bigmodel.cn/api/paas/v4` | `glm-4`, `glm-4-plus` | - Network accessline 51
| **SiliconFlow** | `https://api.siliconflow.cn/v1` | `Qwen/Qwen2.5-72B-Instruct` | - Network accessline 52
| **阿里云百炼** | `https://dashscope.aliyuncs.com/compatible-mode/v1` | `qwen-max` | - Network accessline 53
| **零一万物** | `https://api.lingyiwanwu.com/v1` | `yi-large` | - Network accessline 79
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Network accessline 95
[Credential-related source omitted] - Access to secretsline 95
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Network accessline 160
[Credential-related source omitted] - Access to secretsline 160
[Credential-related source omitted] - Access to secretsline 162
[Credential-related source omitted] - Network accessline 234
- Document everything - Include previous context in round 2+ prompts - Prefer MCP tool over curl when available - Network accessline 236
- Prefer MCP tool over curl when available
skills/skills-codex/auto-review-loop-minimax/SKILL.md
- Network accessline 35
### Method 2: curl (Fallback) - Network accessline 37
If MCP is not available, use curl directly: - Network accessline 40
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Access to secretsline 42
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Network accessline 55
**Why MiniMax instead of a secondary Codex agent?** Codex CLI uses OpenAI's Responses API (`/v1/responses`) which is not supported by third-party providers. See: https://github.com/openai/codex/discussions/7782 - Network accessline 114
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Network accessline 224
- Update project notes after each round, not just at the end - For round 2+, always include previous review context in the prompt - Prefer MCP tool over curl when available (more reliable) - Network accessline 226
- Prefer MCP tool over curl when available (more reliable) - Network accessline 263
**curl Fallback:** - Network accessline 265
[Credential-related source omitted] - Access to secretsline 265
[Credential-related source omitted] - Access to secretsline 267
[Credential-related source omitted]
skills/skills-codex/citation-audit/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Edit, Write, WebSearch, WebFetch, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__clau
skills/skills-codex/citation-crosscheck/SKILL.md
skills/skills-codex/citation-crosscheck/scripts/cx_verify.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 18
ESCALATE routed to the main agent's own primary-source fetch (Step 4) - Network accessline 157
The namespace is KEPT. Stripping both the doi.org and the arxiv.org wrappers to a bare id made 'https://arxiv.org/abs/2301.1' and 'https://doi.org/2301.1' compare - Network accessline 158
bare id made 'https://arxiv.org/abs/2301.1' and 'https://doi.org/2301.1' compare - Network accessline 161
A wrapper with nothing after it ('doi:', 'https://doi.org/') yields '', and an empty - Network accessline 1114
("page range boundary moved", _entry(*_both(pages='1-234', web_pages='12-34')), 'ESCALATE'), ("dash style is still cosmetic", _entry(*_both(pages='12-20', web_pages='12--20')), 'MATCH'), ("arxiv wrapper vs doi wrapper", _entry(*_bot - Network accessline 1115
("dash style is still cosmetic", _entry(*_both(pages='12-20', web_pages='12--20')), 'MATCH'), ("arxiv wrapper vs doi wrapper", _entry(*_both(doi='https://arxiv.org/abs/2301.00001', web_ - Network accessline 1116
("arxiv wrapper vs doi wrapper", _entry(*_both(doi='https://arxiv.org/abs/2301.00001', - Network accessline 1117
web_doi='https://doi.org/2301.00001')), 'ESCALATE'), - Network accessline 1118
("doi resolver prefix is cosmetic", _entry(*_both(doi='https://doi.org/10.1/abc', web_doi='10.1/abc')), 'MATCH'), - Network accessline 1119
("empty identifier is not an identifier", _entry(*_both(doi='doi:', web_doi='https://doi.org/')), 'ESCALATE'), - Network accessline 1144
("same arXiv id in venue, cosmetic form", _entry(*_both(venue='arXiv:2401.00001', web_venue='arxiv 2401.00001')), 'MATCH'), ("preprint-with-id vs known published", _entry(*_both(venue='arXiv:2401.00001', web_venue='ICML')), 'MINOR'), - Network accessline 1145
("preprint-with-id vs known published", _entry(*_both(venue='arXiv:2401.00001', web_venue='ICML')), 'MINOR'), ("url path case is significant", _entry(*_both(url='http://x/Method.pdf', web_url='http://x/method.pdf')), 'ESCALATE'), (" - Network accessline 1146
("url path case is significant", _entry(*_both(url='http://x/Method.pdf', web_url='http://x/method.pdf')), 'ESCALATE'), - Network accessline 1147
("diacritics in an id are significant", _entry(*_both(eprint='Resume', web_eprint='Résumé')), 'ESCALATE'), ("wrong url punctuation", _entry(*_both(url='https://arxiv.org/abs-2401/00001', web_u - Network accessline 1148
("wrong url punctuation", _entry(*_both(url='https://arxiv.org/abs-2401/00001', - Network accessline 1149
web_url='https://arxiv.org/abs/2401.00001')), 'ESCALATE'), - Network accessline 1310
_DOI_REC = "@article{k, title={T}, author={Smith, A}, year={2020}, journal={ICML}, doi={10.1/x}}" _MISC_URL_REC = "@misc{k, title={T}, author={Smith, A}, year={2020}, url={http://example.org/tr}}" - Network accessline 1311
_MISC_URL_REC = "@misc{k, title={T}, author={Smith, A}, year={2020}, url={http://example.org/tr}}" - Network accessline 1557
print('%d entr%s downgraded to ESCALATE for lack of a blindness attestation.' % (downgraded, 'y' if downgraded == 1 else 'ies')) print('ESCALATE entries REQUIRE the main agent\'s own primary-source fetch (Step 4).') - Network accessline 1558
% (downgraded, 'y' if downgraded == 1 else 'ies')) print('ESCALATE entries REQUIRE the main agent\'s own primary-source fetch (Step 4).') print('This gate recomputes the diff from A and B directly (C supplies only flags) and ' - Network accessline 1559
print('ESCALATE entries REQUIRE the main agent\'s own primary-source fetch (Step 4).')
skills/skills-codex/claims-drafting/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__clau
skills/skills-codex/comm-lit-review/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write, mcp__zotero__*, mcp__obsidian-vault__*
skills/skills-codex/deepxiv/SKILL.md
- Network accessline 48
Authentication is handled by the third-party `deepxiv-sdk` CLI using `DEEPXIV_TOKEN`. In [SDK 1.2.2](https://pypi.org/project/deepxiv-sdk/1.2.2/), - Network accessline 49
`DEEPXIV_TOKEN`. In [SDK 1.2.2](https://pypi.org/project/deepxiv-sdk/1.2.2/), - Access to secretsline 52
[Credential-related source omitted]
skills/skills-codex/dse-loop/SKILL.md
- Dangerous shell operationline 16
- `rm -rf`, `rm -r`, or any recursive deletion
skills/skills-codex/embodiment-description/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob
skills/skills-codex/exa-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 39
> - `/exa-search "transformer" — content: summary` — LLM-generated summaries > - `/exa-search "transformer" — domains: arxiv.org,huggingface.co` — domain filter > - `/exa-search "https://arxiv.org/abs/2301.07041" — similar` — find similar p - Network accessline 41
> - `/exa-search "https://arxiv.org/abs/2301.07041" — similar` — find similar pages - Access to secretsline 53
[Credential-related source omitted] - Network accessline 56
Get a key from [exa.ai](https://exa.ai). - Access to secretsline 188
[Credential-related source omitted]
skills/skills-codex/experiment-audit/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/experiment-bridge/SKILL.md
- Network accessline 43
> Override: `/experiment-bridge "EXPERIMENT_PLAN.md" — compact: true, base repo: https://github.com/org/project`
skills/skills-codex/experiment-queue/SKILL.md
skills/skills-codex/feishu-notify/SKILL.md
- Network accessline 23
{ "mode": "push", "webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/YOUR_WEBHOOK_ID", - Network accessline 24
"mode": "push", "webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/YOUR_WEBHOOK_ID", "interactive": { - Network accessline 25
"webhook_url": "https://open.feishu.cn/open-apis/bot/v2/hook/YOUR_WEBHOOK_ID", - Network accessline 26
"interactive": { "bridge_url": "http://localhost:5000", "timeout_seconds": 300 - Network accessline 27
"bridge_url": "http://localhost:5000", - Network accessline 37
| **Off** | `"off"` or file absent | Nothing. Pure CLI as-is | Nothing | | **Push only** | `"push"` | Send webhook notifications at key events. Mobile push, no reply | Feishu bot webhook URL | | **Interactive** | `"interactive"` | Full bidi - Network accessline 39
| **Interactive** | `"interactive"` | Full bidirectional. Approve/reject from Feishu, reply to checkpoints | [feishu-claude-code](https://github.com/joewongjc/feishu-claude-code) running | - Network accessline 59
curl -s -X POST "$WEBHOOK_URL" \ - Network accessline 90
Interactive mode uses [feishu-claude-code](https://github.com/joewongjc/feishu-claude-code) as a bridge: - Network accessline 94
curl -s -X POST "$BRIDGE_URL/send" \ - Network accessline 101
curl -s "$BRIDGE_URL/poll?timeout=$TIMEOUT_SECONDS" - Network accessline 111
- **Push mode**: Check curl exit code. If non-zero, log warning but do NOT block the workflow.
skills/skills-codex/figure-description/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch
skills/skills-codex/figure-spec/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__cla
skills/skills-codex/firecrawl-search/SKILL.md
- Broad permissionsline 1
Bash(*) - Network accessline 41
> - `/firecrawl-search "diffusion transformers" — time: qdr:m` — past month (`qdr:h`, `qdr:d`, `qdr:w`, `qdr:m`, `qdr:y`) > - `/firecrawl-search "LLM agents" — domains: arxiv.org,openreview.net` — domain filter > - `/firecrawl-search "https - Network accessline 43
> - `/firecrawl-search "https://arxiv.org/abs/2211.17192"` — a bare URL is scraped instead of searched - Access to secretsline 50
[Credential-related source omitted] - Network accessline 53
Get a key from [firecrawl.dev](https://www.firecrawl.dev/app/api-keys). Requests without a key are limited to a small daily cap.
skills/skills-codex/gemini-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, mcp__gemini-cli__* - Network accessline 51
3. **gemini-mcp-tool** — MCP bridge for Codex CLI ([jamubc/gemini-mcp-tool](https://github.com/jamubc/gemini-mcp-tool)) - Access to secretsline 69
[Credential-related source omitted] - Network accessline 75
- Free key from [Google AI Studio](https://aistudio.google.com/apikey)
skills/skills-codex/grant-proposal/SKILL.md
- Network accessline 200
- Otherwise invoke `/research-lit` for multi-source literature search (arXiv, Scholar, Zotero, local PDFs) - Search for **funded projects** in the same area via WebSearch: - KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - Network accessline 201
- Search for **funded projects** in the same area via WebSearch: - KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - NSF → NSF Award Search (https://www.nsf.gov/awardsearch/) - Network accessline 202
- KAKENHI → KAKEN database (https://kaken.nii.ac.jp/) - Network accessline 203
- NSF → NSF Award Search (https://www.nsf.gov/awardsearch/)
skills/skills-codex/idea-discovery/SKILL.md
- Network accessline 47
> 💡 These are defaults. Override by telling the skill, e.g., `/idea-discovery "topic" — ref paper: https://arxiv.org/abs/2406.04329` or `/idea-discovery "topic" — compact: true`.
skills/skills-codex/integrity-forensics/SKILL.md
- Network accessline 24
- **ANTI_AR_REPO = `https://github.com/wanshuiyin/Anti-Autoresearch.git`** - Network accessline 38
mkdir -p "$HOME/.aris" if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" - Network accessline 39
if [ ! -d "$CLONE_DIR/.git" ]; then git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR" fi - Network accessline 40
git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR"
skills/skills-codex/interview-cheatsheet/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, spawn_agent, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_st - Network accessline 214
| **<Topic> 面试 Cheat Sheet** | [`<slug>_tutorial.md`](<slug>_tutorial.md) | [`<slug>_tutorial.html`](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/tutorials/<slug>_tutorial.html) | <one-line topic list> |
skills/skills-codex/invention-structuring/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/jurisdiction-format/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob
skills/skills-codex/keenable-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read - Access to secretsline 20
[Credential-related source omitted] - Network accessline 39
> - `/keenable-search "foundation models" — start date: 2025-01-01` (recent pages only) > - `/keenable-search "transformer" — max chars: 8000` (longer snippets) > - `/keenable-search "https://arxiv.org/abs/2209.00796" — fetch` (the page as - Network accessline 41
> - `/keenable-search "https://arxiv.org/abs/2209.00796" — fetch` (the page as markdown) - Access to secretsline 51
[Credential-related source omitted] - Network accessline 54
Create a key in the [Keenable console](https://app.keenable.ai/console). - Access to secretsline 151
[Credential-related source omitted] - Access to secretsline 154
[Credential-related source omitted]
skills/skills-codex/kill-argument/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, spawn_agent, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-revie
skills/skills-codex/lean-formalize/references/lean-working-loop.md
- Network accessline 176
- [Horizon Lean search](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/lean/lean-search/SKILL.md), - Network accessline 177
[proof cycle](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/lean/lean-cycle/SKILL.md), - Network accessline 178
[repair](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/lean/lean-proof-repair/SKILL.md), - Network accessline 179
and [representation experiments](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/review/definition-quality/references/representation-experiments.md). - Network accessline 180
- Horizon acknowledges its selected MIT-licensed adaptations from [cameronfreer/lean4-skills](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/_sources/lean4-ski - Network accessline 181
[cameronfreer/lean4-skills](https://github.com/frenzymath/Archon-Horizon/blob/0df5571f81aae29130c8ec621c9fe7419ca28d6a/src/archon_horizon/pipeline/skills/_sources/lean4-skills/PROVENANCE.md). - Network accessline 182
- [Argus mathematical execution](https://github.com/lbx154/Argus/blob/9cfe9129fd90511c3a1865844ec7dfda1b5d1008/argus/verticals/math/skills/engineer/math-research-execution.md) - Network accessline 183
and [planning](https://github.com/lbx154/Argus/blob/9cfe9129fd90511c3a1865844ec7dfda1b5d1008/argus/verticals/math/skills/planner/math-research-planning.md).
skills/skills-codex/lean-formalize/references/verification-and-handoff.md
- Network accessline 74
steps with suitable proof-producing or kernel-reduced verification. If the task permits a different basis, disclose it accurately. General guidance is in the [Lean reference](https://lean-lang.org/doc/reference/latest/) and the community's - Network accessline 75
permits a different basis, disclose it accurately. General guidance is in the [Lean reference](https://lean-lang.org/doc/reference/latest/) and the community's [native computation discussion](https://leanprover-community.github.io/extras/pi - Network accessline 76
[Lean reference](https://lean-lang.org/doc/reference/latest/) and the community's - Network accessline 77
[native computation discussion](https://leanprover-community.github.io/extras/pitfalls.html#native_decide).
skills/skills-codex/meta-apply/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/meta-optimize/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta - Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta - Network accessline 350
Inspired by [Meta-Harness](https://arxiv.org/abs/2603.28052) (Lee et al., 2026) — end-to-end optimization of model harnesses via filesystem-based experience access and agentic code search. - Network accessline 350
Inspired by [Meta-Harness](https://arxiv.org/abs/2603.28052) (Lee et al., 2026) — end-to-end optimization of model harnesses via filesystem-based experience access and agentic code search.
skills/skills-codex/openalex/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted] - Network accessline 70
3. **Get API keys** (optional but recommended): - **OpenAlex API key**: Free tier $1/day (10,000 list calls, 1,000 search calls) from [openalex.org](https://openalex.org/) - Network accessline 71
- **OpenAlex API key**: Free tier $1/day (10,000 list calls, 1,000 search calls) from [openalex.org](https://openalex.org/)
skills/skills-codex/overleaf-sync/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Edit, Write - Access to secretsline 15
[Credential-related source omitted] - Access to secretsline 27
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 189
[Credential-related source omitted] - Network accessline 195
[Credential-related source omitted] - Access to secretsline 195
[Credential-related source omitted] - Access to secretsline 198
[Credential-related source omitted] - Network accessline 218
- `/citation-audit` — re-run after pulling Overleaf changes that add/edit `\cite{...}` - `/paper-compile` — local LaTeX build; Overleaf compiles independently in the cloud - Overleaf Git bridge docs: https://www.overleaf.com/learn/how-to/Us - Network accessline 220
- Overleaf Git bridge docs: https://www.overleaf.com/learn/how-to/Using_Git_and_GitHub
skills/skills-codex/paper-claim-audit/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/paper-compile/SKILL.md
- Dangerous shell operationline 31
# Ubuntu: sudo apt-get install texlive-full
skills/skills-codex/paper-figure/SKILL.md
- Network accessline 300
- **No decorative elements** — no background colors, no 3D effects, no chart junk - **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if need - Network accessline 301
- **Consistent style across all figures** — same fonts, colors, line widths - **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - **One script per figure** — easy to re-run individual figures when data chang - Network accessline 302
- **Colorblind-safe** — verify with https://davidmathlogic.com/colorblind/ if needed - Network accessline 323
Design pattern (type × style matrix) inspired by [baoyu-skills](https://github.com/jimliu/baoyu-skills). Publication style defaults and figure rules from [pedrohcgs/claude-code-my-workflow](https://github.com/pedrohcgs/claude-code-my-workfl
skills/skills-codex/paper-illustration-image2/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, mcp__codex-image2__generate, mcp__codex-image2__generate_start, mcp__codex-image2__generate_status, spawn_agent, send_input, mcp__antigravity__antigravity, mcp__antigravity__antigravity-rep
skills/skills-codex/paper-illustration-image2/scripts/paper_illustration_image2.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/skills-codex/paper-illustration/SKILL.md
- Access to secretsline 71
[Credential-related source omitted] - Network accessline 160
[Credential-related source omitted] - Access to secretsline 160
[Credential-related source omitted] - Network accessline 161
[Credential-related source omitted] - Access to secretsline 161
[Credential-related source omitted] - Network accessline 162
echo "Get your key from: https://aistudio.google.com/app/apikey" - Access to secretsline 163
[Credential-related source omitted] - Network accessline 280
[Credential-related source omitted] - Access to secretsline 280
[Credential-related source omitted] - Network accessline 281
[Credential-related source omitted] - Access to secretsline 281
[Credential-related source omitted] - Network accessline 313
# Call Gemini gemini-3-pro-preview for layout optimization (DIRECT connection, no proxy) RESPONSE=$(curl -s --max-time 90 \ - Network accessline 314
RESPONSE=$(curl -s --max-time 90 \ - Network accessline 342
[Credential-related source omitted] - Access to secretsline 342
[Credential-related source omitted] - Network accessline 343
[Credential-related source omitted] - Access to secretsline 343
[Credential-related source omitted] - Network accessline 376
# Call Gemini gemini-3-pro-preview for style verification (DIRECT connection, no proxy) RESPONSE=$(curl -s --max-time 90 \ - Network accessline 377
RESPONSE=$(curl -s --max-time 90 \ - Network accessline 412
[Credential-related source omitted] - Access to secretsline 412
[Credential-related source omitted] - Network accessline 413
[Credential-related source omitted] - Access to secretsline 413
[Credential-related source omitted] - Network accessline 441
# Call Paperbanana API WITHOUT proxy (direct connection works better) RESPONSE=$(curl -s --max-time 180 \ - Network accessline 442
RESPONSE=$(curl -s --max-time 180 \ - Possible obfuscationline 470
img_data = base64.b64decode(part['inlineData']['data'])
skills/skills-codex/paper-plan/SKILL.md
- Network accessline 285
Outline methodology inspired by [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (claim-evidence mapping), [claude-scholar](https://github.com/Galaxy-Dawn/claude-scholar) (citation verification),
skills/skills-codex/paper-poster-html/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta - Network accessline 22
via Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen preview lies; only print emulation at the correct viewport tells the truth. Core gate machinery is adapted from [posterly](https://github.com/Chenruishuo/ - Network accessline 23
preview lies; only print emulation at the correct viewport tells the truth. Core gate machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, © 2026 Ruishuo Chen — see `NOTICE.md` and `LICENSES/posterly-MIT.txt` - Network accessline 24
machinery is adapted from [posterly](https://github.com/Chenruishuo/posterly) (MIT, ©
skills/skills-codex/paper-slides/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/paper-talk/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, spawn_agent
skills/skills-codex/paper-write/SKILL.md
- Network accessline 250
#### Verified BibTeX Fetch (when DBLP_BIBTEX = true) - Network accessline 256
# 1. Search by title + first author curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 257
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 258
# 2. Extract DBLP key from result (e.g., conf/nips/VaswaniSPUJGKP17) # 3. Fetch real BibTeX curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 260
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 265
# If paper has a DOI or arXiv ID (arXiv DOI = 10.48550/arXiv.{id}) curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 266
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 488
Principles from [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills): - Network accessline 495
De-AI patterns from [kgraph57/paper-writer-skill](https://github.com/kgraph57/paper-writer-skill): - Network accessline 503
Writing methodology adapted from [Research-Paper-Writing-Skills](https://github.com/Master-cai/Research-Paper-Writing-Skills) (CCF award-winning methodology). Citation verification from [claude-scholar](https://github.com/Galaxy-Dawn/claude
skills/skills-codex/paper-write/templates/IEEEtran.bst
- Network accessline 14
%% %% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 15
%% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ %% http://www.ctan.org/pkg/ieeetran - Network accessline 16
%% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 17
%% http://www.ctan.org/pkg/ieeetran - Network accessline 18
%% and/or %% http://www.ieee.org/ %% - Network accessline 19
%% http://www.ieee.org/ - Network accessline 38
%% %% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 39
%% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, %% distributed and modified. A copy of the LPPL, version 1.3, is included - Network accessline 40
%% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 157
FUNCTION{bst.file.version} { "1.14" } FUNCTION{bst.file.date} { "2015/08/26" } FUNCTION{bst.file.website} { "http://www.michaelshell.org/tex/ieeetran/bibtex/" } - Network accessline 159
FUNCTION{bst.file.website} { "http://www.michaelshell.org/tex/ieeetran/bibtex/" }
skills/skills-codex/paper-write/templates/IEEEtran.cls
- Network accessline 7
%% %% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 8
%% Support sites: %% http://www.michaelshell.org/tex/ieeetran/ %% http://www.ctan.org/pkg/ieeetran - Network accessline 9
%% http://www.michaelshell.org/tex/ieeetran/ - Network accessline 10
%% http://www.ctan.org/pkg/ieeetran - Network accessline 11
%% and %% http://www.ieee.org/ %% - Network accessline 12
%% http://www.ieee.org/ - Network accessline 30
%% Current maintainer (V1.3 to V1.8b): Michael Shell %% See: %% http://www.michaelshell.org/ - Network accessline 31
%% See: %% http://www.michaelshell.org/ %% for current contact information. - Network accessline 32
%% http://www.michaelshell.org/ - Network accessline 52
%% %% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 53
%% This work is distributed under the LaTeX Project Public License (LPPL) %% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, %% distributed and modified. A copy of the LPPL, version 1.3, is included - Network accessline 54
%% ( http://www.latex-project.org/ ) version 1.3, and may be freely used, - Network accessline 138
% the corresponding dvips paper name is "ieeecs". % See the testflow documentation % http://www.ctan.org/tex-archive/macros/latex/contrib/IEEEtran/testflow - Network accessline 139
% See the testflow documentation % http://www.ctan.org/tex-archive/macros/latex/contrib/IEEEtran/testflow % for more details on dvips paper size configuration. - Network accessline 140
% http://www.ctan.org/tex-archive/macros/latex/contrib/IEEEtran/testflow - Network accessline 206
\ProvidesClass{IEEEtran}[2015/08/26 V1.8b by Michael Shell] \typeout{-- See the "IEEEtran_HOWTO" manual for usage information.} \typeout{-- http://www.michaelshell.org/tex/ieeetran/} - Network accessline 207
\typeout{-- See the "IEEEtran_HOWTO" manual for usage information.} \typeout{-- http://www.michaelshell.org/tex/ieeetran/} \NeedsTeXFormat{LaTeX2e} - Network accessline 208
\typeout{-- http://www.michaelshell.org/tex/ieeetran/}
skills/skills-codex/paper-write/templates/aaai2026.sty
- Network accessline 241
\@ifpackageloaded{bbm}% {% \PackageError{aaai}{You must not use bbm package in AAAI papers because it introduces Type 3 fonts which are forbidden.}{See https://tex.stackexchange.com/questions/479160/a-replacement-to-mathbbm1-with- - Network accessline 242
{% \PackageError{aaai}{You must not use bbm package in AAAI papers because it introduces Type 3 fonts which are forbidden.}{See https://tex.stackexchange.com/questions/479160/a-replacement-to-mathbbm1-with-type-1-fonts for possible al - Network accessline 243
\PackageError{aaai}{You must not use bbm package in AAAI papers because it introduces Type 3 fonts which are forbidden.}{See https://tex.stackexchange.com/questions/479160/a-replacement-to-mathbbm1-with-type-1-fonts for possible alternative
skills/skills-codex/paper-write/templates/aaai2026.tex
- Dangerous shell operationline 121
Written by AAAI Press Staff\textsuperscript{\rm 1}\thanks{With help from the AAAI Publications Committee.}\\ - Dangerous shell operationline 132
\textsuperscript{\rm 1}Association for the Advancement of Artificial Intelligence\\ - Dangerous shell operationline 137
% Sunil Issar\textsuperscript{\rm 2}, - Dangerous shell operationline 138
% J. Scott Penberthy\textsuperscript{\rm 3}, - Dangerous shell operationline 139
% George Ferguson\textsuperscript{\rm 4}, - Dangerous shell operationline 140
% Hans Guesgen\textsuperscript{\rm 5} - Dangerous shell operationline 169
First Author Name\textsuperscript{\rm 1}, - Dangerous shell operationline 170
Second Author Name\textsuperscript{\rm 2}, - Dangerous shell operationline 171
Third Author Name\textsuperscript{\rm 1} - Dangerous shell operationline 175
\textsuperscript{\rm 1}Affiliation 1\\ - Dangerous shell operationline 176
\textsuperscript{\rm 2}Affiliation 2\\ - Network accessline 198
% NOTE: For anonymous submissions, do not include links that could reveal your identity % \begin{links} % \link{Code}{https://aaai.org/example/code} - Network accessline 199
% \begin{links} % \link{Code}{https://aaai.org/example/code} % \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 200
% \link{Code}{https://aaai.org/example/code} - Network accessline 201
% \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 202
% \link{Extended version}{https://aaai.org/example/extended-version} - Network accessline 206
% You must keep this block between (not within) the abstract and the main body of the paper. \begin{links} \link{Code}{https://aaai.org/example/code} - Network accessline 207
\begin{links} \link{Code}{https://aaai.org/example/code} \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 208
\link{Code}{https://aaai.org/example/code} - Network accessline 209
\link{Datasets}{https://aaai.org/example/datasets} - Network accessline 210
\link{Extended version}{https://aaai.org/example/extended-version} - Network accessline 405
\begin{scriptsize}\begin{verbatim} \begin{links} \link{Code}{https://aaai.org/example/guidelines} - Network accessline 406
\begin{links} \link{Code}{https://aaai.org/example/guidelines} \link{Datasets}{https://aaai.org/example/datasets} - Network accessline 407
\link{Code}{https://aaai.org/example/guidelines} - Network accessline 408
\link{Datasets}{https://aaai.org/example/datasets} - Network accessline 409
\link{Extended version}{https://aaai.org/example} - Network accessline 525
\subsubsection{Obtaining Type 1 Computer Modern for \LaTeX{}.} If you use Computer Modern for the mathematics in your paper (you cannot use it for the text) you may need to download type 1 Computer fonts. They are available without charge f - Network accessline 527
http://www.ams.org/tex/type1-fonts.html. - Network accessline 532
\subsection{Title and Authors} Your title must appear centered over both text columns in sixteen-point bold type (twenty-four point leading). The title must be written in Title Case capitalization rules (not sentence case). The rules are a - Network accessline 533
Your title must appear centered over both text columns in sixteen-point bold type (twenty-four point leading). The title must be written in Title Case capitalization rules (not sentence case). The rules are a bit involved, but in general ve - Dangerous shell operationline 551
\noindent For authors from different institutions, use \textbackslash textsuperscript \{\textbackslash rm x \} to match authors and affiliations. Notice that there should not be any spaces between the author name (or comma following it) and - Dangerous shell operationline 555
AuthorOne\equalcontrib\textsuperscript{\rm 1,\rm 2}, - Dangerous shell operationline 556
AuthorTwo\equalcontrib\textsuperscript{\rm 2}, - Dangerous shell operationline 557
AuthorThree\textsuperscript{\rm 3},\\ - Dangerous shell operationline 558
AuthorFour\textsuperscript{\rm 4}, - Dangerous shell operationline 559
AuthorFive \textsuperscript{\rm 5}} - Dangerous shell operationline 562
\textsuperscript{\rm 1}AffiliationOne,\\ - Dangerous shell operationline 563
\textsuperscript{\rm 2}AffiliationTwo,\\ - Dangerous shell operationline 564
\textsuperscript{\rm 3}AffiliationThree,\\ - Dangerous shell operationline 565
\textsuperscript{\rm 4}AffiliationFour,\\ - Dangerous shell operationline 566
\textsuperscript{\rm 5}AffiliationFive\\ - Network accessline 849
@misc(key, [...] howpublished="\url{http://...}", - Network accessline 850
[...] howpublished="\url{http://...}", note="Accessed: YYYY-mm-dd", - Network accessline 851
howpublished="\url{http://...}", - Network accessline 859
\vspace{.2em} For the most up to date version of the AAAI reference style, please consult the \textit{AI Magazine} Author Guidelines at \url{https://aaai.org/ojs/index.php/aimagazine/about/submissions#authorGuidelines} - Network accessline 860
For the most up to date version of the AAAI reference style, please consult the \textit{AI Magazine} Author Guidelines at \url{https://aaai.org/ojs/index.php/aimagazine/about/submissions#authorGuidelines}
skills/skills-codex/paper-write/templates/acl.sty
- Network accessline 2
% The official sources can be found at % % https://github.com/acl-org/acl-style-files/ - Network accessline 3
% % https://github.com/acl-org/acl-style-files/ % - Network accessline 4
% https://github.com/acl-org/acl-style-files/ - Network accessline 35
\ifacl@linenumbers % Add draft line numbering via the lineno package % https://texblog.org/2012/02/08/adding-line-numbers-to-documents/ - Network accessline 36
% Add draft line numbering via the lineno package % https://texblog.org/2012/02/08/adding-line-numbers-to-documents/ \usepackage[switch,mathlines]{lineno} - Network accessline 37
% https://texblog.org/2012/02/08/adding-line-numbers-to-documents/ - Network accessline 61
% Patch amsmath commands so that the previous line and the equation itself % are numbered. Bug: multline has an extra line number. % https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align - Network accessline 62
% are numbered. Bug: multline has an extra line number. % https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align \usepackage{etoolbox} %% <- for \pretocmd, \apptocmd and \patchcmd - Network accessline 63
% https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align
skills/skills-codex/paper-write/templates/acl2026.tex
- Network accessline 13
% For Vietnamese characters % \usepackage[T5]{fontenc} % See https://www.latex-project.org/help/documentation/encguide.pdf for other character sets - Network accessline 15
% See https://www.latex-project.org/help/documentation/encguide.pdf for other character sets - Network accessline 117
These instructions are for authors submitting papers to *ACL conferences using \LaTeX. They are not self-contained. All authors must follow the general instructions for *ACL proceedings,\footnote{\url{http://acl-org.github.io/ACLPUB/formatt - Network accessline 298
You can obtain the complete ACL Anthology as a Bib\TeX{} file from \url{https://aclweb.org/anthology/anthology.bib.gz}.
skills/skills-codex/paper-write/templates/acl_natbib.bst
- Network accessline 1
%%% Modification of BibTeX style file acl_natbib_nourl.bst %%% ... by urlbst, version 0.9.1 (marked with "% urlbst") %%% See <https://purl.org/nxg/dist/urlbst> and repository <https://heptapod.host/nxg/urlbst> - Network accessline 2
%%% ... by urlbst, version 0.9.1 (marked with "% urlbst") %%% See <https://purl.org/nxg/dist/urlbst> and repository <https://heptapod.host/nxg/urlbst> %%% Modifications Copyright 2002–23, Norman Gray, - Network accessline 3
%%% See <https://purl.org/nxg/dist/urlbst> and repository <https://heptapod.host/nxg/urlbst> - Network accessline 125
"online" 'onlinestring := % label that a resource is online "[link]" 'linktextstring := % anonymous link text "http://www.ncbi.nlm.nih.gov/pubmed/" 'pubmedurl := % prefix to make URL from PUBMED - Network accessline 126
"[link]" 'linktextstring := % anonymous link text "http://www.ncbi.nlm.nih.gov/pubmed/" 'pubmedurl := % prefix to make URL from PUBMED "https://doi.org/" 'doiurl := % prefix to make URL from DOI - Network accessline 127
"http://www.ncbi.nlm.nih.gov/pubmed/" 'pubmedurl := % prefix to make URL from PUBMED - Network accessline 128
"https://doi.org/" 'doiurl := % prefix to make URL from DOI - Network accessline 129
"doi:" 'doiprefix := % printed text to introduce DOI "https://arxiv.org/abs/" 'eprinturl := % prefix to make URL from eprint ref "cited " 'citedstring := % label in "lastchecked" remark - Network accessline 130
"https://arxiv.org/abs/" 'eprinturl := % prefix to make URL from eprint ref - Network accessline 1191
{ doi empty$ { "" } { doi parse.doi % leaves "https://doi.org/DOI" DOI on the stack - Network accessline 1192
{ "" } { doi parse.doi % leaves "https://doi.org/DOI" DOI on the stack 's := 't := - Network accessline 1193
{ doi parse.doi % leaves "https://doi.org/DOI" DOI on the stack - Network accessline 1231
% then don't print the URL (thanks to Joseph Wright % for (the original version of) this code, % at http://tex.stackexchange.com/questions/5660) - Network accessline 1232
% for (the original version of) this code, % at http://tex.stackexchange.com/questions/5660) adddoi - Network accessline 1233
% at http://tex.stackexchange.com/questions/5660) - Network accessline 1287
% author, note, year, month, and lastchecked fields optional % See references % ISO 690-2 http://www.nlc-bnc.ca/iso/tc46sc9/standard/690-2e.htm - Network accessline 1288
% See references % ISO 690-2 http://www.nlc-bnc.ca/iso/tc46sc9/standard/690-2e.htm % http://www.classroom.net/classroom/CitingNetResources.html - Network accessline 1289
% ISO 690-2 http://www.nlc-bnc.ca/iso/tc46sc9/standard/690-2e.htm - Network accessline 1290
% http://www.classroom.net/classroom/CitingNetResources.html - Network accessline 1291
% http://neal.ctstateu.edu/history/cite.html - Network accessline 1292
% http://www.cas.usf.edu/english/walker/mla.html
skills/skills-codex/paper-write/templates/acm.bst
- Network accessline 557
% result on the output stack, as recommended by CrossRef DOI % documentation. % For example, reduce "http://doi.acm.org/10.1145/1534530.1534545" to - Network accessline 558
% documentation. % For example, reduce "http://doi.acm.org/10.1145/1534530.1534545" to % "10.1145/1534530.1534545". A suitable URL is later typeset and - Network accessline 559
% For example, reduce "http://doi.acm.org/10.1145/1534530.1534545" to - Network accessline 561
% displayed as the LAST item in the reference list entry. Publisher Web % sites wrap this with a suitable link to a real URL to resolve the DOI, % and the master https://doi.org/ address is preferred, since publisher- - Network accessline 562
% sites wrap this with a suitable link to a real URL to resolve the DOI, % and the master https://doi.org/ address is preferred, since publisher- % specific URLs can disappear in response to economic events. All - Network accessline 563
% and the master https://doi.org/ address is preferred, since publisher- - Network accessline 634
%% see output.url for further discussion. "\urldef\tempurl%" writeln "\url{https://doi.org/" strip.doi * "}" * writeln - Network accessline 635
"\urldef\tempurl%" writeln "\url{https://doi.org/" strip.doi * "}" * writeln "\showDOI{\tempurl}" writeln - Network accessline 636
"\url{https://doi.org/" strip.doi * "}" * writeln
skills/skills-codex/paper-write/templates/acm_mm2026.tex
- Network accessline 94
% % The code below should be generated by the tool at % http://dl.acm.org/ccs.cfm - Network accessline 95
% The code below should be generated by the tool at % http://dl.acm.org/ccs.cfm % Please copy and paste the code instead of the example below. - Network accessline 96
% http://dl.acm.org/ccs.cfm - Network accessline 139
Refer to \verb|acmart.pdf| \cite{veytsmanlatex} (\url{https://www.ctan.org/pkg/acmart}, \url{http://www.acm.org/publications/proceedings-template}) for additional examples and instructions.
skills/skills-codex/paper-write/templates/acmart.cls
- Network accessline 860
% Note that the order in which packages are loaded matters, % and the correct order depends on the LaTeX engine used. % See https://github.com/borisveytsman/acmart/issues/402 - Network accessline 861
% and the correct order depends on the LaTeX engine used. % See https://github.com/borisveytsman/acmart/issues/402 % and https://github.com/borisveytsman/acmart/issues/410 - Network accessline 862
% See https://github.com/borisveytsman/acmart/issues/402 - Network accessline 863
% and https://github.com/borisveytsman/acmart/issues/410 - Network accessline 1571
\expandafter\gdef\csname typeset@author\the\num@authors\endcsname##1{% \href{https://orcid.org/#1}{##1}}}} - Network accessline 1572
typeset@author\the\num@authors\endcsname##1{% \href{https://orcid.org/#1}{##1}}}} \def\authorsaddresses#1{\def\@authorsaddresses{#1}} - Network accessline 1573
\href{https://orcid.org/#1}{##1}}}} - Network accessline 1925
Copyright held by the owner/author(s). \fi} \def\@formatdoi#1{\url{https://doi.org/#1}} - Network accessline 1926
\fi} \def\@formatdoi#1{\url{https://doi.org/#1}} \def\@ACM@copyright@check@cc{% - Network accessline 1927
\def\@formatdoi#1{\url{https://doi.org/#1}} - Network accessline 2067
\@ACM@copyright@check@cc \IfEq{\ACM@cc@type}{zero}{% \def\ACM@CC@Url{https://creativecommons.org/publicdomain/zero/1.0/legalcode}}{% - Network accessline 2068
\IfEq{\ACM@cc@type}{zero}{% \def\ACM@CC@Url{https://creativecommons.org/publicdomain/zero/1.0/legalcode}}{% \edef\ACM@CC@Url{https://creativecommons.org/licenses/\ACM@cc@type/\ACM@cc@version/legalcode}}% - Network accessline 2069
\def\ACM@CC@Url{https://creativecommons.org/publicdomain/zero/1.0/legalcode}}{% - Network accessline 2070
\edef\ACM@CC@Url{https://creativecommons.org/licenses/\ACM@cc@type/\ACM@cc@version/legalcode}}% - Network accessline 3483
\def\@tempb{arxiv}% \ifx\@tempa\@tempb\relax arXiv:\href{https://arxiv.org/abs/#2}{#2}% - Network accessline 3484
\ifx\@tempa\@tempb\relax arXiv:\href{https://arxiv.org/abs/#2}{#2}% \else - Network accessline 3485
arXiv:\href{https://arxiv.org/abs/#2}{#2}% - Network accessline 3487
\def\@tempb{arXiv}% \ifx\@tempa\@tempb\relax arXiv:\href{https://arxiv.org/abs/#2}{#2}% - Network accessline 3488
\ifx\@tempa\@tempb\relax arXiv:\href{https://arxiv.org/abs/#2}{#2}% \else - Network accessline 3489
arXiv:\href{https://arxiv.org/abs/#2}{#2}%
skills/skills-codex/paper-write/templates/cvpr.sty
- Network accessline 348
% In review and rebuttal mode, we use the "lineno" package for numbering lines. % When switching to a different mode, the "\@LN" macro may remain in cached .aux files, % leading to build errors (https://github.com/cvpr-org/author-kit/is - Network accessline 349
% When switching to a different mode, the "\@LN" macro may remain in cached .aux files, % leading to build errors (https://github.com/cvpr-org/author-kit/issues/49). % Defining the macro as empty fixes that (https://tex.stackexchange.co - Network accessline 350
% leading to build errors (https://github.com/cvpr-org/author-kit/issues/49). - Network accessline 351
% Defining the macro as empty fixes that (https://tex.stackexchange.com/a/125779). - Network accessline 390
% Patch amsmath commands so that the previous line and the equation itself % are numbered. Bug: multiline has an extra line number. % https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align - Network accessline 391
% are numbered. Bug: multiline has an extra line number. % https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align \RequirePackage{etoolbox} %% <- for \pretocmd, \apptocmd and \patchcmd - Network accessline 392
% https://tex.stackexchange.com/questions/461186/how-to-use-lineno-with-amsmath-align
skills/skills-codex/paper-write/templates/cvpr2026.tex
- Network accessline 1
% CVPR 2026 Paper Template; see https://github.com/cvpr-org/author-kit
skills/skills-codex/paper-write/templates/iclr2026.tex
skills/skills-codex/paper-write/templates/icml2026.tex
- Network accessline 136
are available on the conference web site at: \begin{center} \texttt{http://icml.cc/} - Network accessline 137
\begin{center} \texttt{http://icml.cc/} \end{center} - Network accessline 138
\texttt{http://icml.cc/} - Network accessline 572
for everyone including people with disabilities and sensory or neurological differences. Tips of how to achieve this and what to pay attention to will be provided on the conference website \url{http://icml.cc/}. - Network accessline 574
provided on the conference website \url{http://icml.cc/}.
skills/skills-codex/paper-write/templates/neurips2026.tex
- Network accessline 140
The style files for NeurIPS and other conference information are available on the website at \begin{center} \url{https://neurips.cc}. - Network accessline 141
\begin{center} \url{https://neurips.cc}. \end{center} - Network accessline 142
\url{https://neurips.cc}. - Network accessline 246
The documentation for \verb+natbib+ may be found at \begin{center} \url{http://mirrors.ctan.org/macros/latex/contrib/natbib/natnotes.pdf} - Network accessline 247
\begin{center} \url{http://mirrors.ctan.org/macros/latex/contrib/natbib/natnotes.pdf} \end{center} - Network accessline 248
\url{http://mirrors.ctan.org/macros/latex/contrib/natbib/natnotes.pdf} - Network accessline 331
typesetting high-quality, professional tables: \begin{center} \url{https://www.ctan.org/pkg/booktabs} - Network accessline 332
\begin{center} \url{https://www.ctan.org/pkg/booktabs} \end{center} - Network accessline 333
\url{https://www.ctan.org/pkg/booktabs} - Network accessline 355
\subsection{Math} Note that display math in bare TeX commands will not create correct line numbers for submission. Please use LaTeX (or AMSTeX) commands for unnumbered display math. (You really shouldn't be using \$\$ anyway; see \url{https - Network accessline 356
Note that display math in bare TeX commands will not create correct line numbers for submission. Please use LaTeX (or AMSTeX) commands for unnumbered display math. (You really shouldn't be using \$\$ anyway; see \url{https://tex.stackexchan - Network accessline 427
\end{verbatim} See Section 4.4 in the graphics bundle documentation (\url{http://mirrors.ctan.org/macros/latex/required/graphics/grfguide.pdf}) - Network accessline 429
(\url{http://mirrors.ctan.org/macros/latex/required/graphics/grfguide.pdf}) - Network accessline 438
go at the end of the paper before the list of references. Moreover, you are required to declare funding (financial activities supporting the submitted work) and competing interests (related financial activities outside the submitted work). - Network accessline 440
More information about this disclosure can be found at: \url{https://neurips.cc/Conferences/2026/PaperInformation/FundingDisclosure}.
skills/skills-codex/paper-writing/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__rev - Access to secretsline 52
[Credential-related source omitted] - Access to secretsline 242
[Credential-related source omitted]
skills/skills-codex/patent-novelty-check/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__clau
skills/skills-codex/patent-pipeline/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill
skills/skills-codex/patent-review/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/pixel-art/SKILL.md
- Network accessline 61
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 W H" font-family="monospace">
skills/skills-codex/prior-art-search/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write
skills/skills-codex/proof-checker/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/qzcli/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 12
**GitHub:** [tianyilt/qzcli_tool](https://github.com/tianyilt/qzcli_tool) - Network accessline 25
pip install rich requests prompt_toolkit mcp git clone https://github.com/tianyilt/qzcli_tool - Network accessline 26
git clone https://github.com/tianyilt/qzcli_tool - Access to secretsline 52
[Credential-related source omitted] - Network accessline 58
[Credential-related source omitted] - Network accessline 60
export QZCLI_API_URL="https://qz.yourorg.edu.cn"
skills/skills-codex/rebuttal/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, Skill, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__rev
skills/skills-codex/render-html/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, spawn_agent, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, m - Network accessline 306
For deck / poster / Xiaohongshu card / tweet card / data report style outputs, point users to **[html-anything](https://github.com/nexu-io/html-anything)** (Apache-2.0, 3000⭐ at time of writing). It ships 75 SKILL.md templates across 9 surf
skills/skills-codex/render-html/scripts/render_html.py
- Executable scriptline 1
#!/usr/bin/env python3 - Possible obfuscationline 227
(re.compile(r"^[⚠<U+FE0F>⚠]<U+FE0F>?\s*"), "callout-warn", "Warning"), - Network accessline 708
}; </script> <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js" async></script> - Network accessline 710
<script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js" async></script> - Network accessline 712
<!-- highlight.js --> <link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@11.9.0/build/styles/atom-one-light.min.css"> - Network accessline 713
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@11.9.0/build/styles/atom-one-light.min.css"> - Network accessline 714
<script src="https://cdn.jsdelivr.net/gh/highlightjs/cdn-release@11.9.0/build/highlight.min.js"></script>
skills/skills-codex/render-html/scripts/templates/academic.html
- Network accessline 331
<footer class="aris-footer"> Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> · - Network accessline 332
Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> ·
skills/skills-codex/render-html/scripts/templates/dashboard.html
- Network accessline 323
<footer class="aris-footer"> Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> · - Network accessline 324
Generated by <a href="https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/main/skills/render-html/SKILL.md">ARIS <code>/render-html</code></a> ·
skills/skills-codex/research-implement-feature/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, AskUserQuestion, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-r
skills/skills-codex/research-pipeline/SKILL.md
- Network accessline 56
> 💡 Override via argument, e.g., `/research-pipeline "topic" — AUTO_PROCEED: false, human checkpoint: true, difficulty: nightmare, code review: false, base repo: https://github.com/org/project, auto_write: true, venue: NeurIPS`.
skills/skills-codex/research-wiki/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch - Network accessline 16
Inspired by [Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): compile knowledge once, keep it current, don't re-derive on every query. - Network accessline 421
Inspired by [Karpathy's LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) — "compile knowledge once, keep it current, don't re-derive on every query."
skills/skills-codex/resubmit-pipeline/SKILL.md
skills/skills-codex/result-to-claim/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/run-experiment/SKILL.md
- Access to secretsline 120
[Credential-related source omitted] - Access to secretsline 131
[Credential-related source omitted] - Access to secretsline 133
[Credential-related source omitted] - Dangerous shell operationline 211
- Conda: `eval "$(/opt/conda/bin/conda shell.bash hook)" && conda activate research` - Network accessline 236
[Credential-related source omitted] - Access to secretsline 236
[Credential-related source omitted]
skills/skills-codex/semantic-scholar/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write - Network accessline 96
If `semantic_scholar_fetch.py` is not found, fall back to inline Python using `urllib` against `https://api.semanticscholar.org/graph/v1/paper/search`. - Network accessline 139
For each paper, also show: - **DOI link**: `https://doi.org/DOI` (for IEEE/ACM papers, this is the canonical link) - Network accessline 140
- **DOI link**: `https://doi.org/DOI` (for IEEE/ACM papers, this is the canonical link) - Network accessline 214
- **Venue metadata matters**: Show `venue` and `publicationVenue.type` (journal vs conference) — this helps users assess paper quality. - **DOI is the canonical ID for published papers**: Always show DOI links for IEEE/ACM/Springer papers. - Network accessline 215
- **DOI is the canonical ID for published papers**: Always show DOI links for IEEE/ACM/Springer papers. - **Rate limiting**: S2 API without key is heavily rate-limited (~1 req/s, strict cooldown). If HTTP 429 occurs, wait and retry. Recomme - Network accessline 216
[Credential-related source omitted] - Access to secretsline 216
[Credential-related source omitted]
skills/skills-codex/serverless-modal/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Edit, Write - Network accessline 37
- Sign up: https://modal.com (GitHub/Google login) - Network accessline 38
- Free (no card): **$5/month** — enough for quick tests - Free (with card): **$30/month** — bind a payment method at https://modal.com/settings for the full free tier. Set a **workspace spending limit** to prevent accidental overcharge (Set - Network accessline 39
- Free (with card): **$30/month** — bind a payment method at https://modal.com/settings for the full free tier. Set a **workspace spending limit** to prevent accidental overcharge (Settings → Usage → Spending Limit) - Network accessline 43
> **Recommended setup**: Bind a card to unlock $30/month, then immediately set a spending limit (e.g., $30) so you never exceed the free tier. Modal will pause your workloads when the limit is hit. > > **SECURITY WARNING**: Always bind your - Network accessline 45
> **SECURITY WARNING**: Always bind your card and set spending limits directly on https://modal.com/settings in your browser. NEVER enter payment information, card numbers, or billing details through Codex, Claude Code, or any CLI tool. Onl - Dangerous shell operationline 278
modal volume rm <volume-name> # Delete a volume when done - Network accessline 328
> **Cost protection**: After `modal setup`, go to https://modal.com/settings in your browser (NEVER through CLI) → bind a payment method to unlock $30/month free tier (without card: only $5/month). Then set a **workspace spending limit** eq - Network accessline 332
- Docs: https://modal.com/docs/guide - Network accessline 333
- GPU: https://modal.com/docs/guide/gpu - Network accessline 334
- Pricing: https://modal.com/pricing - Network accessline 335
- Examples: https://modal.com/docs/examples
skills/skills-codex/shared-references/citation-discipline.md
- Network accessline 152
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 152
curl -s "https://dblp.org/search/publ/api?q=TITLE+AUTHOR&format=json&h=3" - Network accessline 153
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 153
curl -s "https://dblp.org/rec/{key}.bib" - Network accessline 159
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}" - Network accessline 159
curl -sLH "Accept: application/x-bibtex" "https://doi.org/{doi}"
skills/skills-codex/shared-references/injection-hygiene.md
- Network accessline 131
> Pattern set adapted from [`NousResearch/hermes-agent`](https://github.com/NousResearch/hermes-agent) - Network accessline 131
> Pattern set adapted from [`NousResearch/hermes-agent`](https://github.com/NousResearch/hermes-agent) - Network accessline 131
> Pattern set adapted from [`NousResearch/hermes-agent`](https://github.com/NousResearch/hermes-agent)
skills/skills-codex/shared-references/integration-contract.md
- Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 238
| `research_wiki.py` (in `/research-wiki` itself) | A (gate) | The SKILL is the wiki tool; missing helper means no functionality | | `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 239
| `verify_wiki_coverage.sh` | E (diagnostic) | Reports coverage gaps; not load-bearing | | `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`) - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC - Network accessline 240
| `cx_verify.py` (in `/citation-crosscheck` Step 3.5) | A (gate) | The fan-out's requirement-(4) **deterministic verifier gate** (`fan-out-pattern.md`): assigns every `MATCH`/`MINOR` granted without a fetch (Step 4 may still resolve an `ESC
skills/skills-codex/shared-references/prior-art-databases.md
- Access to secretsline 56
[Credential-related source omitted]
skills/skills-codex/slides-polish/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, spawn_agent, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-revie
skills/skills-codex/specification-writing/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, WebSearch, WebFetch, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mc
skills/skills-codex/training-check/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_sta
skills/skills-codex/vast-gpu/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob - Access to secretsline 21
[Credential-related source omitted] - Network accessline 26
SSH public key **must be uploaded at https://cloud.vast.ai/manage-keys/ BEFORE creating any instance**. Keys are baked into instances at creation time — if you add a key after renting, you must destroy and re-create the instance. - Access to secretsline 171
[Credential-related source omitted] - Network accessline 211
If SSH fails with "Permission denied (publickey)": - The user's SSH key was not uploaded to https://cloud.vast.ai/manage-keys/ **before** the instance was created - Network accessline 212
- The user's SSH key was not uploaded to https://cloud.vast.ai/manage-keys/ **before** the instance was created
skills/skills-codex/wiki-enrich/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Glob, Grep, WebFetch - Network accessline 16
This contradicts the Karpathy LLM-wiki design (https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): - Network accessline 130
| Order | Source | How | |-------|--------|-----| | 1 | **alphaxiv overview** (`auto` default; `--source alphaxiv` to pin) | `WebFetch https://www.alphaxiv.org/overview/<arxiv_id>.md` — LLM-optimized summary, often best for filling sections - Network accessline 131
|-------|--------|-----| | 1 | **alphaxiv overview** (`auto` default; `--source alphaxiv` to pin) | `WebFetch https://www.alphaxiv.org/overview/<arxiv_id>.md` — LLM-optimized summary, often best for filling sections | | 2 | **alphaxiv abs** - Network accessline 132
| 1 | **alphaxiv overview** (`auto` default; `--source alphaxiv` to pin) | `WebFetch https://www.alphaxiv.org/overview/<arxiv_id>.md` — LLM-optimized summary, often best for filling sections | - Network accessline 133
| 2 | **alphaxiv abs** (fallback within alphaxiv) | `WebFetch https://www.alphaxiv.org/abs/<arxiv_id>.md` | | 3 | **deepxiv brief** (`--source deepxiv` to pin) | `python3 "$DEEPXIV_FETCHER" paper-brief <arxiv_id>` if helper resolves | | 4 | - Network accessline 134
| 3 | **deepxiv brief** (`--source deepxiv` to pin) | `python3 "$DEEPXIV_FETCHER" paper-brief <arxiv_id>` if helper resolves | | 4 | **arXiv API abstract — fresh fetch** (`--source arxiv` to pin) | `curl http://export.arxiv.org/api/query?id - Network accessline 135
| 4 | **arXiv API abstract — fresh fetch** (`--source arxiv` to pin) | `curl http://export.arxiv.org/api/query?id_list=<arxiv_id>` — log label: `arxiv-api-abstract` |
skills/skills-codex/writing-systems-papers/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch
skills/slides-polish/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude
skills/specification-writing/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, Skill, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__
skills/training-check/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Grep, Glob, Write, Edit, mcp__codex__codex, mcp__codex__codex-reply, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__
skills/vast-gpu/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob - Access to secretsline 21
[Credential-related source omitted] - Network accessline 26
SSH public key **must be uploaded at https://cloud.vast.ai/manage-keys/ BEFORE creating any instance**. Keys are baked into instances at creation time — if you add a key after renting, you must destroy and re-create the instance. - Access to secretsline 171
[Credential-related source omitted] - Network accessline 211
If SSH fails with "Permission denied (publickey)": - The user's SSH key was not uploaded to https://cloud.vast.ai/manage-keys/ **before** the instance was created - Network accessline 212
- The user's SSH key was not uploaded to https://cloud.vast.ai/manage-keys/ **before** the instance was created
skills/wiki-enrich/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Glob, Grep, WebFetch - Network accessline 16
This contradicts the Karpathy LLM-wiki design (https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): - Network accessline 132
| Order | Source | How | |-------|--------|-----| | 1 | **alphaxiv overview** (`auto` default; `--source alphaxiv` to pin) | `WebFetch https://www.alphaxiv.org/overview/<arxiv_id>.md` — LLM-optimized summary, often best for filling sections - Network accessline 133
|-------|--------|-----| | 1 | **alphaxiv overview** (`auto` default; `--source alphaxiv` to pin) | `WebFetch https://www.alphaxiv.org/overview/<arxiv_id>.md` — LLM-optimized summary, often best for filling sections | | 2 | **alphaxiv abs** - Network accessline 134
| 1 | **alphaxiv overview** (`auto` default; `--source alphaxiv` to pin) | `WebFetch https://www.alphaxiv.org/overview/<arxiv_id>.md` — LLM-optimized summary, often best for filling sections | - Network accessline 135
| 2 | **alphaxiv abs** (fallback within alphaxiv) | `WebFetch https://www.alphaxiv.org/abs/<arxiv_id>.md` | | 3 | **deepxiv brief** (`--source deepxiv` to pin) | `python3 "$DEEPXIV_FETCHER" paper-brief <arxiv_id>` if helper resolves | | 4 | - Network accessline 136
| 3 | **deepxiv brief** (`--source deepxiv` to pin) | `python3 "$DEEPXIV_FETCHER" paper-brief <arxiv_id>` if helper resolves | | 4 | **arXiv API abstract — fresh fetch** (`--source arxiv` to pin) | `curl http://export.arxiv.org/api/query?id - Network accessline 137
| 4 | **arXiv API abstract — fresh fetch** (`--source arxiv` to pin) | `curl http://export.arxiv.org/api/query?id_list=<arxiv_id>` — log label: `arxiv-api-abstract` |
skills/writing-systems-papers/SKILL.md
- Broad permissionsline 1
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply
tools/arxiv_fetch.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 34
_ATOM_NS = "http://www.w3.org/2005/Atom" - Network accessline 34
_ATOM_NS = "http://www.w3.org/2005/Atom" - Network accessline 34
_ATOM_NS = "http://www.w3.org/2005/Atom" - Network accessline 34
_ATOM_NS = "http://www.w3.org/2005/Atom" - Network accessline 35
_API_BASE = "https://export.arxiv.org/api/query" - Network accessline 35
_API_BASE = "https://export.arxiv.org/api/query" - Network accessline 35
_API_BASE = "https://export.arxiv.org/api/query" - Network accessline 35
_API_BASE = "https://export.arxiv.org/api/query" - Network accessline 59
[Credential-related source omitted] - Network accessline 59
[Credential-related source omitted] - Network accessline 59
[Credential-related source omitted] - Network accessline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Network accessline 60
base = ("arxiv-skill/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 60
base = ("arxiv-skill/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 60
base = ("arxiv-skill/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 60
base = ("arxiv-skill/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 61
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 61
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 61
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 61
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 108
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 108
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 108
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 108
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 109
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 109
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 109
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 109
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 110
Returns the body, or None when curl is missing or the request fails. - Network accessline 110
Returns the body, or None when curl is missing or the request fails. - Network accessline 110
Returns the body, or None when curl is missing or the request fails. - Network accessline 110
Returns the body, or None when curl is missing or the request fails. - Network accessline 112
curl = shutil.which("curl") - Network accessline 112
curl = shutil.which("curl") - Network accessline 112
curl = shutil.which("curl") - Network accessline 112
curl = shutil.which("curl") - Network accessline 113
if curl is None: - Network accessline 113
if curl is None: - Network accessline 113
if curl is None: - Network accessline 113
if curl is None: - Network accessline 130
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 130
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 130
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 130
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 131
req = urllib.request.Request(url, headers=headers) - Network accessline 131
req = urllib.request.Request(url, headers=headers) - Network accessline 131
req = urllib.request.Request(url, headers=headers) - Network accessline 131
req = urllib.request.Request(url, headers=headers) - Network accessline 132
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 132
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 132
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 132
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 133
try: with urllib.request.urlopen(req, timeout=30) as resp: body = resp.read() - Network accessline 133
try: with urllib.request.urlopen(req, timeout=30) as resp: body = resp.read() - Network accessline 133
try: with urllib.request.urlopen(req, timeout=30) as resp: body = resp.read() - Network accessline 133
try: with urllib.request.urlopen(req, timeout=30) as resp: body = resp.read() - Network accessline 134
with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 134
with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 134
with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 134
with urllib.request.urlopen(req, timeout=30) as resp: - Network accessline 183
"updated": updated, "categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 183
"updated": updated, "categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 183
"updated": updated, "categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 183
"updated": updated, "categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 184
"categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", "abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 184
"categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", "abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 184
"categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", "abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 184
"categories": categories, "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", "abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 185
"pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 185
"pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 185
"pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 185
"pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf", - Network accessline 186
"abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 186
"abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 186
"abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 186
"abs_url": f"https://arxiv.org/abs/{arxiv_id}", - Network accessline 225
pdf_url = f"https://arxiv.org/pdf/{clean_id}.pdf" req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 225
pdf_url = f"https://arxiv.org/pdf/{clean_id}.pdf" req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 225
pdf_url = f"https://arxiv.org/pdf/{clean_id}.pdf" req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 225
pdf_url = f"https://arxiv.org/pdf/{clean_id}.pdf" req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 226
req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 226
req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 226
req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 226
req = urllib.request.Request(pdf_url, headers={"User-Agent": _arxiv_user_agent()}) - Network accessline 229
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=60) as resp: - Network accessline 229
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=60) as resp: - Network accessline 229
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=60) as resp: - Network accessline 229
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=60) as resp: - Network accessline 230
try: with urllib.request.urlopen(req, timeout=60) as resp: data = resp.read() - Network accessline 230
try: with urllib.request.urlopen(req, timeout=60) as resp: data = resp.read() - Network accessline 230
try: with urllib.request.urlopen(req, timeout=60) as resp: data = resp.read() - Network accessline 230
try: with urllib.request.urlopen(req, timeout=60) as resp: data = resp.read() - Network accessline 231
with urllib.request.urlopen(req, timeout=60) as resp: - Network accessline 231
with urllib.request.urlopen(req, timeout=60) as resp: - Network accessline 231
with urllib.request.urlopen(req, timeout=60) as resp: - Network accessline 231
with urllib.request.urlopen(req, timeout=60) as resp:
tools/capture_filter.py
tools/deepxiv_fetch.py
tools/evidence_check.py
tools/exa_search.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 52
# Find similar pages to a URL python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 52
# Find similar pages to a URL python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 52
# Find similar pages to a URL python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 52
# Find similar pages to a URL python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 53
python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 53
python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 53
python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 53
python3 tools/exa_search.py find-similar "https://arxiv.org/abs/2301.07041" --max 5 - Network accessline 55
# Get content for specific URLs python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Network accessline 55
# Get content for specific URLs python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Network accessline 55
# Get content for specific URLs python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Network accessline 55
# Get content for specific URLs python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Network accessline 56
python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Network accessline 56
python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Network accessline 56
python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Network accessline 56
python3 tools/exa_search.py get-contents "https://example.com/page1" "https://example.com/page2" - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Access to secretsline 73
[Credential-related source omitted] - Network accessline 74
raise RuntimeError( "EXA_API_KEY environment variable is required. " "Get your key from: https://exa.ai" - Network accessline 74
raise RuntimeError( "EXA_API_KEY environment variable is required. " "Get your key from: https://exa.ai" - Network accessline 74
raise RuntimeError( "EXA_API_KEY environment variable is required. " "Get your key from: https://exa.ai" - Network accessline 74
raise RuntimeError( "EXA_API_KEY environment variable is required. " "Get your key from: https://exa.ai" - Network accessline 75
[Credential-related source omitted] - Network accessline 75
[Credential-related source omitted] - Network accessline 75
[Credential-related source omitted] - Network accessline 75
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Access to secretsline 75
[Credential-related source omitted] - Network accessline 76
"Get your key from: https://exa.ai" - Network accessline 76
"Get your key from: https://exa.ai" - Network accessline 76
"Get your key from: https://exa.ai" - Network accessline 76
"Get your key from: https://exa.ai" - Access to secretsline 84
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted] - Access to secretsline 84
[Credential-related source omitted]
tools/experiment_queue/build_manifest.py
tools/experiment_queue/queue_manager.py
tools/extract_paper_style.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 58
- arXiv ID: arxiv:2501.12345 (fetches abstract HTML) (also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 58
- arXiv ID: arxiv:2501.12345 (fetches abstract HTML) (also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 58
- arXiv ID: arxiv:2501.12345 (fetches abstract HTML) (also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 58
- arXiv ID: arxiv:2501.12345 (fetches abstract HTML) (also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 58
- arXiv ID: arxiv:2501.12345 (fetches abstract HTML) (also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 58
- arXiv ID: arxiv:2501.12345 (fetches abstract HTML) (also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 58
- arXiv ID: arxiv:2501.12345 (fetches abstract HTML) (also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 59
(also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 59
(also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 59
(also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 59
(also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 59
(also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 59
(also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 59
(also: 2501.12345 alone is auto-detected) - HTTP/HTTPS URL: https://... (PDF or HTML) - Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 60
- HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 60
- HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 60
- HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 60
- HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 60
- HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 60
- HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 60
- HTTP/HTTPS URL: https://... (PDF or HTML) - Network accessline 61
- Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 61
- Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 61
- Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 61
- Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 61
- Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 61
- Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 61
- Overleaf URL/ID: https://www.overleaf.com/project/<id> - Network accessline 196
raise MissingDep("requests (pip install requests) needed for arXiv fetch") arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" - Network accessline 196
raise MissingDep("requests (pip install requests) needed for arXiv fetch") arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" - Network accessline 196
raise MissingDep("requests (pip install requests) needed for arXiv fetch") arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" - Network accessline 196
raise MissingDep("requests (pip install requests) needed for arXiv fetch") arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" - Network accessline 196
raise MissingDep("requests (pip install requests) needed for arXiv fetch") arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" - Network accessline 196
raise MissingDep("requests (pip install requests) needed for arXiv fetch") arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" - Network accessline 196
raise MissingDep("requests (pip install requests) needed for arXiv fetch") arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" - Network accessline 197
arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" try: - Network accessline 197
arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" try: - Network accessline 197
arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" try: - Network accessline 197
arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" try: - Network accessline 197
arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" try: - Network accessline 197
arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" try: - Network accessline 197
arxiv_id = arxiv_id.removeprefix("arxiv:") url = f"https://export.arxiv.org/abs/{arxiv_id}" try: - Network accessline 198
url = f"https://export.arxiv.org/abs/{arxiv_id}" try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 198
url = f"https://export.arxiv.org/abs/{arxiv_id}" try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 198
url = f"https://export.arxiv.org/abs/{arxiv_id}" try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 198
url = f"https://export.arxiv.org/abs/{arxiv_id}" try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 198
url = f"https://export.arxiv.org/abs/{arxiv_id}" try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 198
url = f"https://export.arxiv.org/abs/{arxiv_id}" try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 198
url = f"https://export.arxiv.org/abs/{arxiv_id}" try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 199
try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 199
try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 199
try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 199
try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 199
try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 199
try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 199
try: r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 200
r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 200
r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 200
r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 200
r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 200
r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 200
r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 200
r = requests.get(url, timeout=20, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 212
raise MissingDep("requests (pip install requests) needed for HTTP fetch") try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 212
raise MissingDep("requests (pip install requests) needed for HTTP fetch") try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 212
raise MissingDep("requests (pip install requests) needed for HTTP fetch") try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 212
raise MissingDep("requests (pip install requests) needed for HTTP fetch") try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 212
raise MissingDep("requests (pip install requests) needed for HTTP fetch") try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 212
raise MissingDep("requests (pip install requests) needed for HTTP fetch") try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 212
raise MissingDep("requests (pip install requests) needed for HTTP fetch") try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 213
try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 213
try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 213
try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 213
try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 213
try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 213
try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 213
try: r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) except Exception as e: - Network accessline 214
r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 214
r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 214
r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 214
r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 214
r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 214
r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Network accessline 214
r = requests.get(url, timeout=30, headers={"User-Agent": "aris-extract-paper-style/1"}) - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 457
[Credential-related source omitted] - Access to secretsline 457
[Credential-related source omitted]
tools/figure_renderer.py
tools/firecrawl_search.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 11
[Credential-related source omitted] - Access to secretsline 11
[Credential-related source omitted] - Network accessline 30
# Scrape known URLs (HTML or PDF) python3 tools/firecrawl_search.py scrape "https://arxiv.org/abs/2211.17192" - Network accessline 30
# Scrape known URLs (HTML or PDF) python3 tools/firecrawl_search.py scrape "https://arxiv.org/abs/2211.17192" - Network accessline 31
python3 tools/firecrawl_search.py scrape "https://arxiv.org/abs/2211.17192" - Network accessline 31
python3 tools/firecrawl_search.py scrape "https://arxiv.org/abs/2211.17192" - Network accessline 36
import argparse import http.client - Network accessline 36
import argparse import http.client - Network accessline 37
import http.client - Network accessline 37
import http.client - Network accessline 46
API_BASE = "https://api.firecrawl.dev/v2" - Network accessline 46
API_BASE = "https://api.firecrawl.dev/v2" - Network accessline 48
KEY_URL = "https://www.firecrawl.dev/app/api-keys" - Network accessline 48
KEY_URL = "https://www.firecrawl.dev/app/api-keys" - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Network accessline 85
"""Reduce "https://user@ArXiv.org:443/abs?x=1" to "arxiv.org".""" - Network accessline 85
"""Reduce "https://user@ArXiv.org:443/abs?x=1" to "arxiv.org".""" - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 114
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Access to secretsline 127
[Credential-related source omitted] - Access to secretsline 127
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted] - Access to secretsline 129
[Credential-related source omitted] - Access to secretsline 130
[Credential-related source omitted] - Access to secretsline 130
[Credential-related source omitted] - Network accessline 132
request = urllib.request.Request( - Network accessline 132
request = urllib.request.Request( - Network accessline 137
) try: with urllib.request.urlopen(request, timeout=timeout) as response: - Network accessline 137
) try: with urllib.request.urlopen(request, timeout=timeout) as response: - Network accessline 138
try: with urllib.request.urlopen(request, timeout=timeout) as response: raw = response.read() - Network accessline 138
try: with urllib.request.urlopen(request, timeout=timeout) as response: raw = response.read() - Network accessline 139
with urllib.request.urlopen(request, timeout=timeout) as response: - Network accessline 139
with urllib.request.urlopen(request, timeout=timeout) as response: - Network accessline 142
try: body = json.loads(exc.read() or b"{}") except (ValueError, OSError, http.client.HTTPException): - Network accessline 142
try: body = json.loads(exc.read() or b"{}") except (ValueError, OSError, http.client.HTTPException): - Network accessline 143
body = json.loads(exc.read() or b"{}") except (ValueError, OSError, http.client.HTTPException): body = None - Network accessline 143
body = json.loads(exc.read() or b"{}") except (ValueError, OSError, http.client.HTTPException): body = None - Network accessline 144
except (ValueError, OSError, http.client.HTTPException): - Network accessline 144
except (ValueError, OSError, http.client.HTTPException): - Access to secretsline 147
[Credential-related source omitted] - Access to secretsline 147
[Credential-related source omitted] - Network accessline 148
except urllib.error.URLError as exc: raise RuntimeError(f"Could not reach the Firecrawl API: {exc.reason}") from None except (TimeoutError, OSError, http.client.HTTPException) as exc: - Network accessline 148
except urllib.error.URLError as exc: raise RuntimeError(f"Could not reach the Firecrawl API: {exc.reason}") from None except (TimeoutError, OSError, http.client.HTTPException) as exc: - Network accessline 150
except (TimeoutError, OSError, http.client.HTTPException) as exc: - Network accessline 150
except (TimeoutError, OSError, http.client.HTTPException) as exc: - Access to secretsline 377
[Credential-related source omitted] - Access to secretsline 377
[Credential-related source omitted]
tools/forensics_gate.py
- Executable scriptline 1
#!/usr/bin/env python3
tools/install_aris.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 401
rm -f "$tmp" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 442
rm -f "$avail_f" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 489
rm -f "$glist" "$ungrouped" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 591
rm -f "$new_file" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 605
rm -f "$excl" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 762
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 782
rm -rf "$LOCK_DIR" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 796
same_path "$current_target_path" "$LEAF_AGENT_SOURCE" && rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 810
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 815
rm -f "$MANIFEST_TMP" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 818
[[ -n "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_ROLLBACK_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 819
[[ -n "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" ]] && rm -f "$LEAF_AGENT_MANIFEST_WRITTEN_SNAPSHOT" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 851
$DRY_RUN || rm -f "$LEGACY_NESTED" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1030
rm -f "$target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1046
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1047
else rm -f "$target_path"; log " - $name" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1104
log " (dry-run) rm $link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1106
rm -f "$link_path" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1236
rm -f "$LEAF_AGENT_MANIFEST_PATH" - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1253
cp "$AGENT_PROFILE_MANIFEST_PATH" "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1257
printf '%s\n' "$name" >> "$unsorted" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1258
sort -u "$unsorted" > "$tmp" || { rm -f "$unsorted" "$tmp"; return 1; } - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1259
rm -f "$unsorted" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1298
rm -f "$target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1328
log " (dry-run) rm $target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1330
rm -f "$target" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1342
rm -f "$AGENT_PROFILE_MANIFEST_PATH" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1415
rm -f "$LEAF_AGENT_TARGET" - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1447
on) rm -f "$AGENT_PROFILES_OPT_OUT_PATH" ;; - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1523
rm -f "$tmp" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1570
if $DRY_RUN; then log " (dry-run) rm $target_path" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1571
else rm -f "$target_path"; log " - removed $name" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1574
rm -f "$manifest_data" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1742
rm -f "$INSTALLED_NAMES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES" - Dangerous shell operationline 1760
rm -f "$UPSTREAM_FILE" "$MANIFEST_DATA" "$PLAN_FILE" "$SELECTED_FILE" "$SELECTED_UPSTREAM" "$DECLINED_CANDIDATES"
tools/iteration_log.py
tools/keenable_search.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 10
[Credential-related source omitted] - Network accessline 10
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Network accessline 12
https://app.keenable.ai/console). - Network accessline 12
https://app.keenable.ai/console). - Network accessline 43
# Fetch pages as markdown python3 tools/keenable_search.py fetch "https://arxiv.org/abs/2209.00796" - Network accessline 43
# Fetch pages as markdown python3 tools/keenable_search.py fetch "https://arxiv.org/abs/2209.00796" - Network accessline 44
python3 tools/keenable_search.py fetch "https://arxiv.org/abs/2209.00796" - Network accessline 44
python3 tools/keenable_search.py fetch "https://arxiv.org/abs/2209.00796" - Network accessline 61
_API_BASE = "https://api.keenable.ai" - Network accessline 61
_API_BASE = "https://api.keenable.ai" - Access to secretsline 70
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Network accessline 113
data = json.dumps(payload).encode("utf-8") headers["Content-Type"] = "application/json" req = urllib.request.Request(url, data=data, headers=headers) - Network accessline 113
data = json.dumps(payload).encode("utf-8") headers["Content-Type"] = "application/json" req = urllib.request.Request(url, data=data, headers=headers) - Network accessline 114
headers["Content-Type"] = "application/json" req = urllib.request.Request(url, data=data, headers=headers) last_err: Exception | None = None - Network accessline 114
headers["Content-Type"] = "application/json" req = urllib.request.Request(url, data=data, headers=headers) last_err: Exception | None = None - Network accessline 115
req = urllib.request.Request(url, data=data, headers=headers) - Network accessline 115
req = urllib.request.Request(url, data=data, headers=headers) - Network accessline 118
for attempt in range(retries + 1): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 118
for attempt in range(retries + 1): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 119
try: with urllib.request.urlopen(req, timeout=timeout) as resp: raw = resp.read().decode("utf-8") - Network accessline 119
try: with urllib.request.urlopen(req, timeout=timeout) as resp: raw = resp.read().decode("utf-8") - Network accessline 120
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 120
with urllib.request.urlopen(req, timeout=timeout) as resp: - Access to secretsline 139
[Credential-related source omitted] - Access to secretsline 139
[Credential-related source omitted] - Network accessline 232
def fetch(urls: list[str], max_chars: int = 10000) -> dict[str, Any]: - Network accessline 232
def fetch(urls: list[str], max_chars: int = 10000) -> dict[str, Any]: - Network accessline 339
if args.command == "fetch": result = fetch(urls=args.urls, max_chars=args.max_chars) - Network accessline 339
if args.command == "fetch": result = fetch(urls=args.urls, max_chars=args.max_chars) - Network accessline 340
result = fetch(urls=args.urls, max_chars=args.max_chars) - Network accessline 340
result = fetch(urls=args.urls, max_chars=args.max_chars)
tools/meta_opt/trigger_eval.py
tools/openalex_fetch.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 2
""" OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ - Network accessline 2
""" OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ - Network accessline 2
""" OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ - Network accessline 2
""" OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ - Network accessline 3
OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ """ - Network accessline 3
OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ """ - Network accessline 3
OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ """ - Network accessline 3
OpenAlex API client for academic paper search. Documentation: https://developers.openalex.org/ """ - Network accessline 4
Documentation: https://developers.openalex.org/ - Network accessline 4
Documentation: https://developers.openalex.org/ - Network accessline 4
Documentation: https://developers.openalex.org/ - Network accessline 4
Documentation: https://developers.openalex.org/ - Network accessline 26
class OpenAlexClient: BASE_URL = "https://api.openalex.org" - Network accessline 26
class OpenAlexClient: BASE_URL = "https://api.openalex.org" - Network accessline 26
class OpenAlexClient: BASE_URL = "https://api.openalex.org" - Network accessline 26
class OpenAlexClient: BASE_URL = "https://api.openalex.org" - Network accessline 27
BASE_URL = "https://api.openalex.org" - Network accessline 27
BASE_URL = "https://api.openalex.org" - Network accessline 27
BASE_URL = "https://api.openalex.org" - Network accessline 27
BASE_URL = "https://api.openalex.org" - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Network accessline 37
[Credential-related source omitted] - Network accessline 37
[Credential-related source omitted] - Network accessline 37
[Credential-related source omitted] - Network accessline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted] - Network accessline 39
self.session = requests.Session() - Network accessline 39
self.session = requests.Session() - Network accessline 39
self.session = requests.Session() - Network accessline 39
self.session = requests.Session() - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 96
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Access to secretsline 97
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Access to secretsline 138
[Credential-related source omitted] - Network accessline 173
"id": work.get("id"), "openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, - Network accessline 173
"id": work.get("id"), "openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, - Network accessline 173
"id": work.get("id"), "openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, - Network accessline 173
"id": work.get("id"), "openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, - Network accessline 174
"openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, "title": work.get("display_name") or work.get("title", "Untitled"), - Network accessline 174
"openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, "title": work.get("display_name") or work.get("title", "Untitled"), - Network accessline 174
"openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, "title": work.get("display_name") or work.get("title", "Untitled"), - Network accessline 174
"openalex_id": work.get("id", "").split("/")[-1], "doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, "title": work.get("display_name") or work.get("title", "Untitled"), - Network accessline 175
"doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, - Network accessline 175
"doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, - Network accessline 175
"doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None, - Network accessline 175
"doi": work.get("doi", "").replace("https://doi.org/", "") if work.get("doi") else None,
tools/overleaf_audit.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Network accessline 65
echo "" echo " Token may already be public if pushed. Revoke immediately:" echo " https://www.overleaf.com/user/settings" - Network accessline 65
echo "" echo " Token may already be public if pushed. Revoke immediately:" echo " https://www.overleaf.com/user/settings" - Network accessline 66
echo " Token may already be public if pushed. Revoke immediately:" echo " https://www.overleaf.com/user/settings" FOUND=1 - Network accessline 66
echo " Token may already be public if pushed. Revoke immediately:" echo " https://www.overleaf.com/user/settings" FOUND=1 - Network accessline 67
echo " https://www.overleaf.com/user/settings" - Network accessline 67
echo " https://www.overleaf.com/user/settings" - Access to secretsline 79
[Credential-related source omitted] - Access to secretsline 79
[Credential-related source omitted] - Network accessline 97
echo "" echo "Action items:" echo " 1. Revoke the leaked token at https://www.overleaf.com/user/settings" - Network accessline 97
echo "" echo "Action items:" echo " 1. Revoke the leaked token at https://www.overleaf.com/user/settings" - Network accessline 98
echo "Action items:" echo " 1. Revoke the leaked token at https://www.overleaf.com/user/settings" echo " 2. Generate a new token" - Network accessline 98
echo "Action items:" echo " 1. Revoke the leaked token at https://www.overleaf.com/user/settings" echo " 2. Generate a new token" - Network accessline 99
echo " 1. Revoke the leaked token at https://www.overleaf.com/user/settings" - Network accessline 99
echo " 1. Revoke the leaked token at https://www.overleaf.com/user/settings"
tools/overleaf_setup.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 6
[Credential-related source omitted] - Access to secretsline 6
[Credential-related source omitted] - Network accessline 11
# # Example: # bash tools/overleaf_setup.sh https://www.overleaf.com/project/69e478... paper-overleaf - Network accessline 11
# # Example: # bash tools/overleaf_setup.sh https://www.overleaf.com/project/69e478... paper-overleaf - Network accessline 13
# bash tools/overleaf_setup.sh https://www.overleaf.com/project/69e478... paper-overleaf - Network accessline 13
# bash tools/overleaf_setup.sh https://www.overleaf.com/project/69e478... paper-overleaf - Network accessline 27
echo "Usage: $0 <project-id-or-url> [clone-dir]" echo "" echo " project-id-or-url: e.g. 'abc123def456' or 'https://www.overleaf.com/project/abc123def456'" - Network accessline 27
echo "Usage: $0 <project-id-or-url> [clone-dir]" echo "" echo " project-id-or-url: e.g. 'abc123def456' or 'https://www.overleaf.com/project/abc123def456'" - Network accessline 28
echo "" echo " project-id-or-url: e.g. 'abc123def456' or 'https://www.overleaf.com/project/abc123def456'" echo " clone-dir: defaults to 'paper-overleaf'" - Network accessline 28
echo "" echo " project-id-or-url: e.g. 'abc123def456' or 'https://www.overleaf.com/project/abc123def456'" echo " clone-dir: defaults to 'paper-overleaf'" - Network accessline 29
echo " project-id-or-url: e.g. 'abc123def456' or 'https://www.overleaf.com/project/abc123def456'" - Network accessline 29
echo " project-id-or-url: e.g. 'abc123def456' or 'https://www.overleaf.com/project/abc123def456'" - Network accessline 52
echo "Setting up Overleaf bridge for project $PROJECT_ID → ./$CLONE_DIR/" echo "" echo "Get a token at: https://www.overleaf.com/user/settings → Git Integration → Create Token" - Network accessline 52
echo "Setting up Overleaf bridge for project $PROJECT_ID → ./$CLONE_DIR/" echo "" echo "Get a token at: https://www.overleaf.com/user/settings → Git Integration → Create Token" - Network accessline 53
echo "" echo "Get a token at: https://www.overleaf.com/user/settings → Git Integration → Create Token" echo "" - Network accessline 53
echo "" echo "Get a token at: https://www.overleaf.com/user/settings → Git Integration → Create Token" echo "" - Network accessline 54
echo "Get a token at: https://www.overleaf.com/user/settings → Git Integration → Create Token" - Network accessline 54
echo "Get a token at: https://www.overleaf.com/user/settings → Git Integration → Create Token" - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 63
[Credential-related source omitted] - Access to secretsline 63
[Credential-related source omitted] - Network accessline 68
echo "Cloning…" if ! git clone "https://git:${OL_TOKEN}@git.overleaf.com/${PROJECT_ID}" "$CLONE_DIR" 2>&1 \ - Network accessline 68
echo "Cloning…" if ! git clone "https://git:${OL_TOKEN}@git.overleaf.com/${PROJECT_ID}" "$CLONE_DIR" 2>&1 \ - Network accessline 69
[Credential-related source omitted] - Network accessline 69
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Access to secretsline 70
[Credential-related source omitted] - Network accessline 77
cd "$CLONE_DIR" git remote set-url origin "https://git.overleaf.com/${PROJECT_ID}" - Network accessline 77
cd "$CLONE_DIR" git remote set-url origin "https://git.overleaf.com/${PROJECT_ID}" - Network accessline 78
git remote set-url origin "https://git.overleaf.com/${PROJECT_ID}" - Network accessline 78
git remote set-url origin "https://git.overleaf.com/${PROJECT_ID}" - Access to secretsline 95
[Credential-related source omitted] - Access to secretsline 95
[Credential-related source omitted] - Network accessline 112
echo "ERROR: Overleaf token pattern (olp_…) detected in staged changes." echo " Refusing to commit. Remove the token before committing." echo " Also revoke it at https://www.overleaf.com/user/settings" - Network accessline 112
echo "ERROR: Overleaf token pattern (olp_…) detected in staged changes." echo " Refusing to commit. Remove the token before committing." echo " Also revoke it at https://www.overleaf.com/user/settings" - Network accessline 113
echo " Refusing to commit. Remove the token before committing." echo " Also revoke it at https://www.overleaf.com/user/settings" exit 1 - Network accessline 113
echo " Refusing to commit. Remove the token before committing." echo " Also revoke it at https://www.overleaf.com/user/settings" exit 1 - Network accessline 114
echo " Also revoke it at https://www.overleaf.com/user/settings" - Network accessline 114
echo " Also revoke it at https://www.overleaf.com/user/settings" - Dangerous shell operationline 124
cd .. && rm -rf "$CLONE_DIR" - Dangerous shell operationline 124
cd .. && rm -rf "$CLONE_DIR"
tools/paper_illustration_image2.py
tools/provenance.py
- Executable scriptline 1
#!/usr/bin/env python3
tools/research_wiki.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 78
_ARXIV_API = "https://export.arxiv.org/api/query?id_list={ids}" - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 79
_ARXIV_NS = {"atom": "http://www.w3.org/2005/Atom", - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 80
"arxiv": "http://arxiv.org/schemas/atom"} - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Network accessline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted] - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 94
base = ("ARIS-research-wiki/1.0 " "(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") return f"{base} (mailto:{contact})" if contact else base - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 95
"(+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)") - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 464
s = arxiv_id.strip() for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 465
for prefix in ("arXiv:", "arxiv:", "http://arxiv.org/abs/", "https://arxiv.org/abs/"): - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 490
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 491
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 492
Returns the body, or None when curl is missing or the request fails. - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 494
curl = shutil.which("curl") - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 495
if curl is None: - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 513
headers = {"User-Agent": _arxiv_user_agent()} req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 514
req = urllib.request.Request(url, headers=headers) - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 515
for attempt in (1, 2, 3): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 516
try: with urllib.request.urlopen(req, timeout=timeout) as resp: body = resp.read() - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 517
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 564
# The <id> element holds e.g. http://arxiv.org/abs/2510.23672v1 — recover - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1443
then each page is written from the pre-fetched metadata — N papers cost 1 arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1444
arXiv request instead of N, avoiding the burst-429 problem. Ids the batch did not return fall back to a per-id fetch (handles the occasional miss). Dedup is still handled per-id inside ingest_paper. - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss). - Network accessline 1445
did not return fall back to a per-id fetch (handles the occasional miss).
tools/review_gate.py
- Executable scriptline 1
#!/usr/bin/env python3
tools/run_state.py
tools/semantic_scholar_fetch.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 57
_API_BASE = "https://api.semanticscholar.org/graph/v1" _USER_AGENT = "s2-fetch/1.1" - Network accessline 57
_API_BASE = "https://api.semanticscholar.org/graph/v1" _USER_AGENT = "s2-fetch/1.1" - Network accessline 57
_API_BASE = "https://api.semanticscholar.org/graph/v1" _USER_AGENT = "s2-fetch/1.1" - Network accessline 57
_API_BASE = "https://api.semanticscholar.org/graph/v1" _USER_AGENT = "s2-fetch/1.1" - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 80
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Network accessline 86
def _request_json(url: str, *, retries: int = 2, timeout: int = _DEFAULT_TIMEOUT) -> dict[str, Any]: req = urllib.request.Request(url, headers=_headers()) - Network accessline 86
def _request_json(url: str, *, retries: int = 2, timeout: int = _DEFAULT_TIMEOUT) -> dict[str, Any]: req = urllib.request.Request(url, headers=_headers()) - Network accessline 86
def _request_json(url: str, *, retries: int = 2, timeout: int = _DEFAULT_TIMEOUT) -> dict[str, Any]: req = urllib.request.Request(url, headers=_headers()) - Network accessline 86
def _request_json(url: str, *, retries: int = 2, timeout: int = _DEFAULT_TIMEOUT) -> dict[str, Any]: req = urllib.request.Request(url, headers=_headers()) - Network accessline 87
req = urllib.request.Request(url, headers=_headers()) - Network accessline 87
req = urllib.request.Request(url, headers=_headers()) - Network accessline 87
req = urllib.request.Request(url, headers=_headers()) - Network accessline 87
req = urllib.request.Request(url, headers=_headers()) - Network accessline 90
for attempt in range(retries + 1): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 90
for attempt in range(retries + 1): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 90
for attempt in range(retries + 1): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 90
for attempt in range(retries + 1): try: with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 91
try: with urllib.request.urlopen(req, timeout=timeout) as resp: raw = resp.read().decode("utf-8") - Network accessline 91
try: with urllib.request.urlopen(req, timeout=timeout) as resp: raw = resp.read().decode("utf-8") - Network accessline 91
try: with urllib.request.urlopen(req, timeout=timeout) as resp: raw = resp.read().decode("utf-8") - Network accessline 91
try: with urllib.request.urlopen(req, timeout=timeout) as resp: raw = resp.read().decode("utf-8") - Network accessline 92
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 92
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 92
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 92
with urllib.request.urlopen(req, timeout=timeout) as resp:
tools/skill_picker.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3
tools/smart_update.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Access to secretsline 208
[Credential-related source omitted] - Access to secretsline 209
[Credential-related source omitted] - Dangerous shell operationline 539
rm -rf "$LOCAL_DIR/$s" - Dangerous shell operationline 547
rm -rf "$LOCAL_DIR/shared-references"
tools/threat_scan.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Instruction override signalline 32
The (?:\\w+\\s+)* filler-gap between key tokens defeats "ignore all PRIOR instructions"-style evasion. """ - Instruction override signalline 32
The (?:\\w+\\s+)* filler-gap between key tokens defeats "ignore all PRIOR instructions"-style evasion. """ - Access to secretsline 83
[Credential-related source omitted] - Access to secretsline 83
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Access to secretsline 85
[Credential-related source omitted] - Network accessline 86
# Require explicit exfil intent — "upload your SSH key at https://..." (legit - Network accessline 86
# Require explicit exfil intent — "upload your SSH key at https://..." (legit - Network accessline 87
# setup) must NOT trip; "exfiltrate the data to https://..." must. - Network accessline 87
# setup) must NOT trip; "exfiltrate the data to https://..." must. - Possible obfuscationline 108
'<U+200B>', '<U+200C>', '<U+200D>', '<U+2060>', '<U+2062>', '<U+2063>', '<U+2064>', - Possible obfuscationline 108
'<U+200B>', '<U+200C>', '<U+200D>', '<U+2060>', '<U+2062>', '<U+2063>', '<U+2064>', - Possible obfuscationline 109
'<U+FEFF>', '<U+202A>', '<U+202B>', '<U+202C>', '<U+202D>', '<U+202E>', - Possible obfuscationline 109
'<U+FEFF>', '<U+202A>', '<U+202B>', '<U+202C>', '<U+202D>', '<U+202E>', - Possible obfuscationline 110
'<U+2066>', '<U+2067>', '<U+2068>', '<U+2069>', - Possible obfuscationline 110
'<U+2066>', '<U+2067>', '<U+2068>', '<U+2069>',
tools/verify_paper_audits.sh
tools/verify_papers.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 108
ARXIV_API = "https://export.arxiv.org/api/query" - Network accessline 109
CROSSREF_API = "https://api.crossref.org/works" - Network accessline 110
S2_API = "https://api.semanticscholar.org/graph/v1/paper/search" - Network accessline 124
def _arxiv_user_agent() -> str: contact = os.environ.get("ARIS_VERIFY_EMAIL", "").strip() base = "verify-papers/1.0 (+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)" - Network accessline 125
[Credential-related source omitted] - Access to secretsline 125
[Credential-related source omitted] - Network accessline 126
base = "verify-papers/1.0 (+https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep)" - Network accessline 170
def normalize_doi(raw: str) -> str: return raw.strip().lower().lstrip("https://doi.org/").lstrip("doi.org/") - Network accessline 171
return raw.strip().lower().lstrip("https://doi.org/").lstrip("doi.org/") - Network accessline 239
export.arxiv.org refuses urllib from some networks for minutes at a time while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 240
while curl gets 200 on the same URL, so retrying urllib cannot recover. - Network accessline 241
Returns the body, or None when curl is missing or the request fails. - Network accessline 243
curl = shutil.which("curl") - Network accessline 244
if curl is None: - Network accessline 256
An HTTP 406 is re-issued once through curl before it is reported. - Network accessline 258
req = urllib.request.Request(url, headers=headers or {}) - Network accessline 259
try: with urllib.request.urlopen(req, timeout=timeout) as resp: return resp.status, resp.read().decode("utf-8", errors="replace") - Network accessline 260
with urllib.request.urlopen(req, timeout=timeout) as resp: - Network accessline 316
found = set() for bid in base_ids: if f"<id>http://arxiv.org/abs/{bid}" in body: - Network accessline 317
for bid in base_ids: if f"<id>http://arxiv.org/abs/{bid}" in body: found.add(bid) - Network accessline 318
if f"<id>http://arxiv.org/abs/{bid}" in body: - Access to secretsline 371
[Credential-related source omitted] - Access to secretsline 372
[Credential-related source omitted] - Access to secretsline 654
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 24 facts
- Allows Bash without restrictions, though it has no scripts or shell blocksablation-planner/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksanalyze-results/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksclaims-drafting/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blockscomm-lit-review/SKILL.md:4High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksdse-loop/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksembodiment-description/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksexperiment-audit/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksexperiment-plan/SKILL.md:4High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksfigure-description/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksidea-discovery-robot/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksidea-discovery/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksinvention-structuring/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksjurisdiction-format/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blockslean-formalize/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksnovelty-check/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blockspaper-claim-audit/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blockspaper-talk/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blockspatent-novelty-check/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blockspatent-pipeline/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksprior-art-search/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksrebuttal/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksresearch-implement-feature/SKILL.md:5High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksresearch-refine-pipeline/SKILL.md:4High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksresearch-refine/SKILL.md:4High confidence
Signal confidence: 476 facts
- Broad permissions in the frontmatter of the SKILL.mdablation-planner/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdalphaxiv/SKILL.md:1High confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:29Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:30Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:31Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:34Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:35Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:36Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:46Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:47Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:48Low confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:49Low confidence
- Network access in code of the SKILL.mdalphaxiv/SKILL.md:62High confidence
- Network access in code of the SKILL.mdalphaxiv/SKILL.md:76High confidence
- Network access in prose of the SKILL.mdalphaxiv/SKILL.md:88Low confidence
- Network access in code of the SKILL.mdalphaxiv/SKILL.md:109High confidence
- Broad permissions in the frontmatter of the SKILL.mdanalyze-results/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdarxiv/SKILL.md:1High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:76High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:77High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:78High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:79High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:80High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:81High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:96High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:97High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:98High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:99High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:120High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:121High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:122High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:123High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:124High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:148High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:149High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:150High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:151High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:152High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:153High confidence
- Network access in code of the SKILL.mdarxiv/SKILL.md:154High confidence
- Broad permissions in the frontmatter of the SKILL.mdauto-paper-improvement-loop/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdauto-review-loop-llm/SKILL.md:1High confidence
- Network access in code of the SKILL.mdauto-review-loop-llm/SKILL.md:44High confidence
- Network access in code of the SKILL.mdauto-review-loop-llm/SKILL.md:45High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueauto-review-loop-llm/SKILL.md:45Low confidence
- Network access in code of the SKILL.mdauto-review-loop-llm/SKILL.md:46High confidence
- Network access in prose of the SKILL.mdauto-review-loop-llm/SKILL.md:56Low confidence
- Network access in prose of the SKILL.mdauto-review-loop-llm/SKILL.md:57Low confidence
- Network access in prose of the SKILL.mdauto-review-loop-llm/SKILL.md:58Low confidence
and 426 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/ablation-planner/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/ablation-planner/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/ablation-planner/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/ablation-planner/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/ablation-planner/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/wanshuiyin-auto-claude-code-research-in-sleep/)