#195 by GitHub stars
tw93/Waza
🥷 Engineering habits you already know, turned into skills AI assistants like Claude Code, Codex and Cursor can run.
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
plugins/waza/skills/check/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → df1ef2390e89
No earlier version was observed for comparison.
plugins/waza/skills/health/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → df1ef2390e89
No earlier version was observed for comparison.
plugins/waza/skills/hunt/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
plugins/waza/skills/learn/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
plugins/waza/skills/read/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → df1ef2390e89
No earlier version was observed for comparison.
plugins/waza/skills/think/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
plugins/waza/skills/ui/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
plugins/waza/skills/write/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/check/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/health/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/hunt/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/learn/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/read/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/think/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/ui/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → df1ef2390e89
No earlier version was observed for comparison.
skills/write/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → df1ef2390e89
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit df1ef2390e89d70dee07f928ac09aa7ba4b90299
git clone --filter=blob:none --no-checkout https://github.com/tw93/Waza.git .hotskills/tw93-waza && git -C .hotskills/tw93-waza checkout --detach df1ef2390e89d70dee07f928ac09aa7ba4b90299
# Copy each selected skill directory from .hotskills/tw93-waza into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/tw93/Waza.git .hotskills/tw93-waza && git -C .hotskills/tw93-waza checkout --detach df1ef2390e89d70dee07f928ac09aa7ba4b90299
# Copy each selected skill directory from .hotskills/tw93-waza into .agents/skills/<skill-name>/7.5kGitHub stars
40stars in 7 days
16skills in this repository
59commits in 30 days
Heat
6.4- Star growth, last 7 daysAhead of 75% of tracked repositories
- Star growth, last 24 hoursAhead of 67% of tracked repositories
- Rank movement, last 7 daysAhead of 63% of tracked repositories
- Commits, last 30 daysAhead of 91% 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
- check
plugins/waza/skills/check - health
plugins/waza/skills/health - hunt
plugins/waza/skills/hunt - learn
plugins/waza/skills/learn - read
plugins/waza/skills/read - think
plugins/waza/skills/think - ui
plugins/waza/skills/ui - write
plugins/waza/skills/write - check
skills/check - health
skills/health - hunt
skills/hunt - learn
skills/learn - read
skills/read - think
skills/think - ui
skills/ui - write
skills/write
How it works
check
When your agent uses it
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
5,986 tokensWhen the skill is activated
Reference documents
11,123 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Worktree Safety Preflight
- Mode Picker
- Project Context Extraction
- Plan Execution Mode
- Get the Diff
- Scope
- Did We Build What Was Asked?
- Question the Approach, Not Just the Diff
- Pattern-Fix Completeness
- Command And Install Surfaces
- Hard Rules
- Hard Stops (fix before merging)
- Finding Quality Gate
- Knowledge Sync
- Specialist Review (Standard and Deep only)
- Autofix Routing
- Adversarial Pass (Deep only)
- Platform Operations
- Verification
- Gotchas
- Sign-off
Scripts executed separately
scripts/audit_signals.pyscripts/incident_ledger.pyscripts/release_gate.pyscripts/run-tests.sh
Files
../../../../.claude-plugin/marketplace.jsonasset4,516 bytes../../../../.claude-plugin/marketplace.jsonasset4,516 bytesSKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesagents/reviewer-architecture.mddoc2,318 bytesagents/reviewer-security.mddoc2,703 bytesreferences/durable-context.mddoc2,042 bytesreferences/incident-ledger.mddoc3,594 bytesreferences/mode-audit.mddoc3,014 bytesreferences/mode-ship.mddoc8,773 bytesreferences/mode-triage.mddoc4,941 bytesreferences/persona-catalog.mddoc3,525 bytesreferences/project-context.mddoc9,608 bytesreferences/public-reply.mddoc1,764 bytesreferences/release-surfaces.mddoc3,709 bytesreferences/review-patterns.mddoc7,631 bytesscripts/audit_signals.pyruns25,992 bytesscripts/incident_ledger.pyruns13,080 bytesscripts/release_gate.pyruns14,586 bytesscripts/run-tests.shruns639 bytes
Read SKILL.md
# Check: Review Before You Ship
Prefix your first line with 🥷 inline, not as its own paragraph.
> Note: `/review` is a built-in Anthropic plugin command for PR review. Waza uses `/check` (or the alias `code-review`) instead. Do not re-trigger `/review` from within this skill.
Read the diff and find the problems. Review, audit, triage, and readiness requests are report-only; apply fixes only under explicit repair authorization still in force for the same task. Done means the requested review surface is covered and every verification claim comes from this session.
## Outcome Contract
- Outcome: a review, release decision, or maintainer action grounded in the current diff, project context, and live evidence.
- Done when: findings, fixes, shipped state, or blockers are stated with the commands, artifacts, or remote state that prove them.
- Evidence: worktree status, diff, public project docs, manifests, CI, package contents, release or registry state, and current command output.
- Output: concise findings first, then verification and shipped-state summary when applicable. Multi-step or ship-action runs, and any request with several items or screenshots, close with a numbered completion ledger (done / not applicable / remaining), never a narrative that leaves the user asking "is everything done".health
When your agent uses it
Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
4,506 tokensWhen the skill is activated
Reference documents
7,283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Hard Rules
- Step 0: Establish the evidence basis
- Step 1: Collect data
- Step 1b: Runtime Inventory and MCP Check
- Step 1c: Safety and security checks
- Step 2: Analyze
- Gotchas
- Output
Scripts executed separately
scripts/block-pipe-to-shell.pyscripts/check-agent-context.shscripts/check-doc-refs.shscripts/check-maintainability.shscripts/check-verifier-output.shscripts/check_agent_context.pyscripts/check_doc_refs.pyscripts/check_maintainability.pyscripts/check_verifier_output.pyscripts/collect-data.shscripts/conversation_audit.pyscripts/read_skill_description.pyscripts/run-health.ps1scripts/scan_skill_security.py
Files
SKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesagents/inspector-context.mddoc11,858 bytesagents/inspector-control.mddoc6,144 bytesagents/inspector-maintainability.mddoc3,653 bytesreferences/durable-context.mddoc2,042 bytesreferences/long-running-agents.mddoc1,804 bytesreferences/maintainability-findings.mddoc9,526 bytesscripts/block-pipe-to-shell.pyruns11,631 bytesscripts/check-agent-context.shruns2,694 bytesscripts/check-doc-refs.shruns2,682 bytesscripts/check-maintainability.shruns2,696 bytesscripts/check-verifier-output.shruns2,696 bytesscripts/check_agent_context.pyruns70,059 bytesscripts/check_doc_refs.pyruns6,952 bytesscripts/check_maintainability.pyruns44,407 bytesscripts/check_verifier_output.pyruns3,561 bytesscripts/collect-data.shruns40,088 bytesscripts/conversation_audit.pyruns35,269 bytesscripts/read_skill_description.pyruns1,694 bytesscripts/run-health.ps1runs14,480 bytesscripts/scan_skill_security.pyruns19,946 bytes
Read SKILL.md
# Health: Agent-Assisted Engineering Health
Prefix your first line with 🥷 inline, not as its own paragraph.
Audit the current project's agent setup and AI coding maintainability against this framework:
`agent config → instruction surfaces → tools/runtime → verifiers → maintainability`
Find violations. Identify the misaligned layer. Calibrate to evidence and risk, not repository size.
## Outcome Contract
- Outcome: a budget-aware health report that separates agent configuration risk from AI maintainability risk.
- Done when: each finding names the misaligned layer, the concrete evidence, and a copy-pasteable action or diagnostic command.
- Evidence: collected health script output, tracked project instructions, runtime config summaries, verifier logs, hooks/MCP surfaces, and read-only live probes when needed.hunt
When your agent uses it
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
3,693 tokensWhen the skill is activated
Reference documents
5,738 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Diagnosis Signals
- Durable Context Preflight
- Bisect Mode
- Repeated Regression / Screenshot Reference Mode
- Scope Blast Mode
- Confirm or Discard
- Runtime Evidence Ladder
- Native App Freeze Mode
- Targeted Logging
- Rendering Bug Mode
- IME / Unicode Issues
- Hard Rules
- Gotchas
- Output
Files
SKILL.mdcore17,253 bytesSKILL.mdcore17,253 bytesSKILL.mdcore17,253 bytesreferences/durable-context.mddoc2,042 bytesreferences/failure-patterns.mddoc15,232 bytesreferences/ime-unicode.mddoc4,671 bytesreferences/logging-techniques.mddoc3,810 bytesreferences/rendering-debug.mddoc1,356 bytes
Read SKILL.md
# Hunt: Diagnose Before You Fix
Prefix your first line with 🥷 inline, not as its own paragraph.
A patch applied to a symptom creates a new bug somewhere else.
## Outcome Contract
- Outcome: the root cause is identified before any fix is applied.
- Done when: one sentence explains the cause, every observed symptom fits it, and the fix or handoff is verified against a reproducible check.
- Evidence: source trace, repro command or UI path, logs or state, targeted test/build output, and runtime evidence for UI or native defects.
- Output: root cause, fix or handoff, verification result, and any unswept sibling risks.
[Credential-related source omitted]
learn
When your agent uses it
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,869 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
- Outcome Contract
- Choose Mode
- Canonical Article Mode
- Phase 1: Collect
- Phase 2: Digest
- Phase 3: Outline
- Phase 4: Fill In
- Phase 5: Refine
- Phase 6: Self-review and Publish Readiness
- Hard Rules
- Gotchas
- Output
Files
SKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytes
Read SKILL.md
# Learn: From Raw Materials to Published Output
Prefix your first line with 🥷 inline, not as its own paragraph.
Support the user's thinking; do not replace it.
## Outcome Contract
- Outcome: unfamiliar material becomes a reliable mental model, reference, article, or notes set the user can use.
- Done when: primary sources are collected or supplied, contradictions are handled explicitly, and the final structure teaches the topic without hiding uncertainty.
- Evidence: source URLs or files, fetched content, notes from digestion, outline decisions, and self-review against the requested output.
- Output: research notes, outline, publish-ready draft, or canonical reference, matching the chosen mode.
**Boundary**: single URL that only needs fetching belongs in `/read`. A single URL that needs summary or analysis can use `/read` as the fetch step, but the final answer should satisfy the user's requested summary or analysis. `/learn` is for multi-source research that produces a new structured output.read
When your agent uses it
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
1,783 tokensWhen the skill is activated
Reference documents
1,332 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Routing
- Privacy and Fetch Tiers
- Saving
- Images
- Content Extraction for Restyling
- Hard Rules
- Gotchas
- Output
Scripts executed separately
scripts/deepseek.pyscripts/fetch.shscripts/fetch_feishu.pyscripts/fetch_local.pyscripts/fetch_weixin.py
Files
SKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesreferences/read-methods.mddoc5,312 bytesscripts/deepseek.pyruns3,953 bytesscripts/fetch.shruns3,998 bytesscripts/fetch_feishu.pyruns9,137 bytesscripts/fetch_local.pyruns7,276 bytesscripts/fetch_weixin.pyruns3,717 bytes
Read SKILL.md
# Read: Read Any URL or PDF
Prefix your first line with 🥷 inline, not as its own paragraph.
Fetch any URL or local PDF.
## Outcome Contract
- Outcome: the user gets the useful content from a URL or PDF in the form they asked for.
- Done when: the answer is grounded in fetched content, paywall or extraction failures are explicit, and saved files are only created when requested or needed downstream.
- Evidence: original URL or file path, fetch tier, extracted text or metadata, and warning signals from the fetched content.
- Output: concise summary, clean Markdown, saved file path, quotes, citations, or extracted details, depending on the request.
- Plain "read this" / "看这个链接" requests: return a concise source-grounded summary, not a full Markdown dump.think
When your agent uses it
Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
2,470 tokensWhen the skill is activated
Reference documents
1,335 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Lightweight Mode
- Evaluation Mode
- Triage Mode
- Before Reading Any Code
- Check for Official Solutions First
- Propose Approaches
- Validate Before Handing Off
- Simplicity Gate
- Implementation Handoff
- Hard Rules
- Gotchas
- Output
Files
SKILL.mdcore11,944 bytesSKILL.mdcore11,944 bytesreferences/durable-context.mddoc2,042 bytesreferences/mode-evaluation.mddoc2,756 bytesreferences/mode-triage.mddoc1,768 bytes
Read SKILL.md
# Think: Design and Validate Before You Build
Prefix your first line with 🥷 inline, not as its own paragraph.
Turn a rough idea into an approved plan. No code, no scaffolding, no pseudo-code until the user approves.
Give opinions directly. Take a position and state what evidence would change it. Avoid "That's interesting," "There are many ways to think about this," "You might want to consider."
## Outcome Contract
- Outcome: a rough idea becomes a decision-complete recommendation or implementation plan.
- Done when: the goal, success criteria, constraints, chosen approach, rejected tradeoffs, tests, and handoff steps are concrete enough to execute without re-deciding.
- Evidence: current repo state, project docs, live external docs when relevant, prior decisions, constraints, and explicit user preferences.
- Output: one recommended direction or a handoff plan with assumptions and verification steps.ui
When your agent uses it
Produces distinctive production UI and screenshot-grounded visual polish. Use when building or restyling pages, components, or typography. Not for backend logic or data pipelines.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
3,139 tokensWhen the skill is activated
Reference documents
11,649 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Mode Picker
- Lock the Direction First
- When Asked For Options
- Hard Rules
- Gotchas
- Output: Aesthetic Review
Files
SKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesreferences/design-data-viz.mddoc2,615 bytesreferences/design-native-motion.mddoc3,706 bytesreferences/design-reference.mddoc31,256 bytesreferences/durable-context.mddoc2,042 bytesreferences/mode-generated-asset.mddoc3,766 bytesreferences/mode-quick-fix.mddoc4,418 bytesreferences/mode-screenshot-iteration.mddoc5,768 bytes
Read SKILL.md
# UI: Build It With a Point of View
Prefix your first line with 🥷 inline, not as its own paragraph.
If it could have been generated by a default prompt, it is not good enough.
## Outcome Contract
- Outcome: a usable interface or visual fix with a clear point of view and no incoherent layout, text, or responsive breakage.
- Done when: the real rendered surface or generated artifact has been checked against the user's visual goal and the relevant viewport states.
- Evidence: screenshots, rendered UI, source components, design tokens, accessibility constraints, and user-provided references.
- Output: the implemented visual change or a precise visual review with the remaining verification gap named.
**Output language rule:** Never use U+2014 em dash in any output from this skill. Use commas, colons, or periods instead.write
When your agent uses it
Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing, localizing, or cutting AI tone. Not for code comments or commit messages.
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
3,291 tokensWhen the skill is activated
Reference documents
26,948 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Core Stance
- Pre-flight
- Mode Picker
- Document Review Mode
- Paragraph Coherence Mode
- Tweet / Social Post Mode
- Hard Rules
- Punctuation Gate
- Gotchas
- Output
Scripts executed separately
scripts/check-punctuation.shscripts/check_punctuation.py
Files
SKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesreferences/durable-context.mddoc2,042 bytesreferences/mode-long-form.mddoc2,556 bytesreferences/mode-public-reply.mddoc4,385 bytesreferences/mode-release-notes.mddoc4,454 bytesreferences/mode-revision-review.mddoc3,231 bytesreferences/write-en.mddoc9,473 bytesreferences/write-product-localization.mddoc13,257 bytesreferences/write-technical.mddoc8,691 bytesreferences/write-zh-bilingual.mddoc1,498 bytesreferences/write-zh-release-notes.mddoc2,368 bytesreferences/write-zh.mddoc55,014 bytesscripts/check-punctuation.shruns151 bytesscripts/check_punctuation.pyruns19,323 bytes
Read SKILL.md
# Write: Cut the AI Taste
Prefix your first line with 🥷 inline, not as its own paragraph.
Strip AI patterns from prose and rewrite it to sound human. Do not improve vocabulary; remove the performance of improvement.
## Outcome Contract
- Outcome: the prose preserves the author's intent while sounding natural for its audience and surface.
- Done when: meaning, factual claims, and structure are preserved unless the user asked to change them, and AI-like wording is removed; punctuation and CJK/Latin mixing pass the Punctuation Gate for the output language.
- Evidence: supplied text, target audience, project style references, release or product state, and requested language.
- Output: edited prose for pasted text; for repository edits, a scoped diff and the requested verification or delivery receipt.
## Durable Context Preflightcheck
When your agent uses it
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
5,986 tokensWhen the skill is activated
Reference documents
11,123 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Worktree Safety Preflight
- Mode Picker
- Project Context Extraction
- Plan Execution Mode
- Get the Diff
- Scope
- Did We Build What Was Asked?
- Question the Approach, Not Just the Diff
- Pattern-Fix Completeness
- Command And Install Surfaces
- Hard Rules
- Hard Stops (fix before merging)
- Finding Quality Gate
- Knowledge Sync
- Specialist Review (Standard and Deep only)
- Autofix Routing
- Adversarial Pass (Deep only)
- Platform Operations
- Verification
- Gotchas
- Sign-off
Scripts executed separately
scripts/audit_signals.pyscripts/incident_ledger.pyscripts/release_gate.pyscripts/run-tests.sh
Files
SKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesSKILL.mdcore28,228 bytesagents/reviewer-architecture.mddoc2,318 bytesagents/reviewer-security.mddoc2,703 bytesreferences/durable-context.mddoc2,042 bytesreferences/incident-ledger.mddoc3,594 bytesreferences/mode-audit.mddoc3,014 bytesreferences/mode-ship.mddoc8,773 bytesreferences/mode-triage.mddoc4,941 bytesreferences/persona-catalog.mddoc3,525 bytesreferences/project-context.mddoc9,608 bytesreferences/public-reply.mddoc1,764 bytesreferences/release-surfaces.mddoc3,709 bytesreferences/review-patterns.mddoc7,631 bytesscripts/audit_signals.pyruns25,992 bytesscripts/incident_ledger.pyruns13,080 bytesscripts/release_gate.pyruns14,586 bytesscripts/run-tests.shruns639 bytes
Read SKILL.md
# Check: Review Before You Ship
Prefix your first line with 🥷 inline, not as its own paragraph.
> Note: `/review` is a built-in Anthropic plugin command for PR review. Waza uses `/check` (or the alias `code-review`) instead. Do not re-trigger `/review` from within this skill.
Read the diff and find the problems. Review, audit, triage, and readiness requests are report-only; apply fixes only under explicit repair authorization still in force for the same task. Done means the requested review surface is covered and every verification claim comes from this session.
## Outcome Contract
- Outcome: a review, release decision, or maintainer action grounded in the current diff, project context, and live evidence.
- Done when: findings, fixes, shipped state, or blockers are stated with the commands, artifacts, or remote state that prove them.
- Evidence: worktree status, diff, public project docs, manifests, CI, package contents, release or registry state, and current command output.
- Output: concise findings first, then verification and shipped-state summary when applicable. Multi-step or ship-action runs, and any request with several items or screenshots, close with a numbered completion ledger (done / not applicable / remaining), never a narrative that leaves the user asking "is everything done".health
When your agent uses it
Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
4,506 tokensWhen the skill is activated
Reference documents
7,283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Hard Rules
- Step 0: Establish the evidence basis
- Step 1: Collect data
- Step 1b: Runtime Inventory and MCP Check
- Step 1c: Safety and security checks
- Step 2: Analyze
- Gotchas
- Output
Scripts executed separately
scripts/block-pipe-to-shell.pyscripts/check-agent-context.shscripts/check-doc-refs.shscripts/check-maintainability.shscripts/check-verifier-output.shscripts/check_agent_context.pyscripts/check_doc_refs.pyscripts/check_maintainability.pyscripts/check_verifier_output.pyscripts/collect-data.shscripts/conversation_audit.pyscripts/read_skill_description.pyscripts/run-health.ps1scripts/scan_skill_security.py
Files
SKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesSKILL.mdcore21,233 bytesagents/inspector-context.mddoc11,858 bytesagents/inspector-control.mddoc6,144 bytesagents/inspector-maintainability.mddoc3,653 bytesreferences/durable-context.mddoc2,042 bytesreferences/long-running-agents.mddoc1,804 bytesreferences/maintainability-findings.mddoc9,526 bytesscripts/block-pipe-to-shell.pyruns11,631 bytesscripts/check-agent-context.shruns2,694 bytesscripts/check-doc-refs.shruns2,682 bytesscripts/check-maintainability.shruns2,696 bytesscripts/check-verifier-output.shruns2,696 bytesscripts/check_agent_context.pyruns70,059 bytesscripts/check_doc_refs.pyruns6,952 bytesscripts/check_maintainability.pyruns44,407 bytesscripts/check_verifier_output.pyruns3,561 bytesscripts/collect-data.shruns40,088 bytesscripts/conversation_audit.pyruns35,269 bytesscripts/read_skill_description.pyruns1,694 bytesscripts/run-health.ps1runs14,480 bytesscripts/scan_skill_security.pyruns19,946 bytes
Read SKILL.md
# Health: Agent-Assisted Engineering Health
Prefix your first line with 🥷 inline, not as its own paragraph.
Audit the current project's agent setup and AI coding maintainability against this framework:
`agent config → instruction surfaces → tools/runtime → verifiers → maintainability`
Find violations. Identify the misaligned layer. Calibrate to evidence and risk, not repository size.
## Outcome Contract
- Outcome: a budget-aware health report that separates agent configuration risk from AI maintainability risk.
- Done when: each finding names the misaligned layer, the concrete evidence, and a copy-pasteable action or diagnostic command.
- Evidence: collected health script output, tracked project instructions, runtime config summaries, verifier logs, hooks/MCP surfaces, and read-only live probes when needed.hunt
When your agent uses it
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
3,693 tokensWhen the skill is activated
Reference documents
5,738 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Diagnosis Signals
- Durable Context Preflight
- Bisect Mode
- Repeated Regression / Screenshot Reference Mode
- Scope Blast Mode
- Confirm or Discard
- Runtime Evidence Ladder
- Native App Freeze Mode
- Targeted Logging
- Rendering Bug Mode
- IME / Unicode Issues
- Hard Rules
- Gotchas
- Output
Files
SKILL.mdcore17,253 bytesSKILL.mdcore17,253 bytesSKILL.mdcore17,253 bytesreferences/durable-context.mddoc2,042 bytesreferences/failure-patterns.mddoc15,232 bytesreferences/ime-unicode.mddoc4,671 bytesreferences/logging-techniques.mddoc3,810 bytesreferences/rendering-debug.mddoc1,356 bytes
Read SKILL.md
# Hunt: Diagnose Before You Fix
Prefix your first line with 🥷 inline, not as its own paragraph.
A patch applied to a symptom creates a new bug somewhere else.
## Outcome Contract
- Outcome: the root cause is identified before any fix is applied.
- Done when: one sentence explains the cause, every observed symptom fits it, and the fix or handoff is verified against a reproducible check.
- Evidence: source trace, repro command or UI path, logs or state, targeted test/build output, and runtime evidence for UI or native defects.
- Output: root cause, fix or handoff, verification result, and any unswept sibling risks.
[Credential-related source omitted]
learn
When your agent uses it
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,869 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
- Outcome Contract
- Choose Mode
- Canonical Article Mode
- Phase 1: Collect
- Phase 2: Digest
- Phase 3: Outline
- Phase 4: Fill In
- Phase 5: Refine
- Phase 6: Self-review and Publish Readiness
- Hard Rules
- Gotchas
- Output
Files
SKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytesSKILL.mdcore8,984 bytes
Read SKILL.md
# Learn: From Raw Materials to Published Output
Prefix your first line with 🥷 inline, not as its own paragraph.
Support the user's thinking; do not replace it.
## Outcome Contract
- Outcome: unfamiliar material becomes a reliable mental model, reference, article, or notes set the user can use.
- Done when: primary sources are collected or supplied, contradictions are handled explicitly, and the final structure teaches the topic without hiding uncertainty.
- Evidence: source URLs or files, fetched content, notes from digestion, outline decisions, and self-review against the requested output.
- Output: research notes, outline, publish-ready draft, or canonical reference, matching the chosen mode.
**Boundary**: single URL that only needs fetching belongs in `/read`. A single URL that needs summary or analysis can use `/read` as the fetch step, but the final answer should satisfy the user's requested summary or analysis. `/learn` is for multi-source research that produces a new structured output.read
When your agent uses it
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
1,783 tokensWhen the skill is activated
Reference documents
1,332 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Routing
- Privacy and Fetch Tiers
- Saving
- Images
- Content Extraction for Restyling
- Hard Rules
- Gotchas
- Output
Scripts executed separately
scripts/deepseek.pyscripts/fetch.shscripts/fetch_feishu.pyscripts/fetch_local.pyscripts/fetch_weixin.py
Files
SKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesSKILL.mdcore7,903 bytesreferences/read-methods.mddoc5,312 bytesscripts/deepseek.pyruns3,953 bytesscripts/fetch.shruns3,998 bytesscripts/fetch_feishu.pyruns9,137 bytesscripts/fetch_local.pyruns7,276 bytesscripts/fetch_weixin.pyruns3,717 bytes
Read SKILL.md
# Read: Read Any URL or PDF
Prefix your first line with 🥷 inline, not as its own paragraph.
Fetch any URL or local PDF.
## Outcome Contract
- Outcome: the user gets the useful content from a URL or PDF in the form they asked for.
- Done when: the answer is grounded in fetched content, paywall or extraction failures are explicit, and saved files are only created when requested or needed downstream.
- Evidence: original URL or file path, fetch tier, extracted text or metadata, and warning signals from the fetched content.
- Output: concise summary, clean Markdown, saved file path, quotes, citations, or extracted details, depending on the request.
- Plain "read this" / "看这个链接" requests: return a concise source-grounded summary, not a full Markdown dump.think
When your agent uses it
Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
2,470 tokensWhen the skill is activated
Reference documents
1,335 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Lightweight Mode
- Evaluation Mode
- Triage Mode
- Before Reading Any Code
- Check for Official Solutions First
- Propose Approaches
- Validate Before Handing Off
- Simplicity Gate
- Implementation Handoff
- Hard Rules
- Gotchas
- Output
Files
SKILL.mdcore11,944 bytesSKILL.mdcore11,944 bytesreferences/durable-context.mddoc2,042 bytesreferences/mode-evaluation.mddoc2,756 bytesreferences/mode-triage.mddoc1,768 bytes
Read SKILL.md
# Think: Design and Validate Before You Build
Prefix your first line with 🥷 inline, not as its own paragraph.
Turn a rough idea into an approved plan. No code, no scaffolding, no pseudo-code until the user approves.
Give opinions directly. Take a position and state what evidence would change it. Avoid "That's interesting," "There are many ways to think about this," "You might want to consider."
## Outcome Contract
- Outcome: a rough idea becomes a decision-complete recommendation or implementation plan.
- Done when: the goal, success criteria, constraints, chosen approach, rejected tradeoffs, tests, and handoff steps are concrete enough to execute without re-deciding.
- Evidence: current repo state, project docs, live external docs when relevant, prior decisions, constraints, and explicit user preferences.
- Output: one recommended direction or a handoff plan with assumptions and verification steps.ui
When your agent uses it
Produces distinctive production UI and screenshot-grounded visual polish. Use when building or restyling pages, components, or typography. Not for backend logic or data pipelines.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
3,139 tokensWhen the skill is activated
Reference documents
11,649 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Mode Picker
- Lock the Direction First
- When Asked For Options
- Hard Rules
- Gotchas
- Output: Aesthetic Review
Files
SKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesSKILL.mdcore15,271 bytesreferences/design-data-viz.mddoc2,615 bytesreferences/design-native-motion.mddoc3,706 bytesreferences/design-reference.mddoc31,256 bytesreferences/durable-context.mddoc2,042 bytesreferences/mode-generated-asset.mddoc3,766 bytesreferences/mode-quick-fix.mddoc4,418 bytesreferences/mode-screenshot-iteration.mddoc5,768 bytes
Read SKILL.md
# UI: Build It With a Point of View
Prefix your first line with 🥷 inline, not as its own paragraph.
If it could have been generated by a default prompt, it is not good enough.
## Outcome Contract
- Outcome: a usable interface or visual fix with a clear point of view and no incoherent layout, text, or responsive breakage.
- Done when: the real rendered surface or generated artifact has been checked against the user's visual goal and the relevant viewport states.
- Evidence: screenshots, rendered UI, source components, design tokens, accessibility constraints, and user-provided references.
- Output: the implemented visual change or a precise visual review with the remaining verification gap named.
**Output language rule:** Never use U+2014 em dash in any output from this skill. Use commas, colons, or periods instead.write
When your agent uses it
Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing, localizing, or cutting AI tone. Not for code comments or commit messages.
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
3,291 tokensWhen the skill is activated
Reference documents
26,948 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outcome Contract
- Durable Context Preflight
- Core Stance
- Pre-flight
- Mode Picker
- Document Review Mode
- Paragraph Coherence Mode
- Tweet / Social Post Mode
- Hard Rules
- Punctuation Gate
- Gotchas
- Output
Scripts executed separately
scripts/check-punctuation.shscripts/check_punctuation.py
Files
SKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesSKILL.mdcore15,845 bytesreferences/durable-context.mddoc2,042 bytesreferences/mode-long-form.mddoc2,556 bytesreferences/mode-public-reply.mddoc4,385 bytesreferences/mode-release-notes.mddoc4,454 bytesreferences/mode-revision-review.mddoc3,231 bytesreferences/write-en.mddoc9,473 bytesreferences/write-product-localization.mddoc13,257 bytesreferences/write-technical.mddoc8,691 bytesreferences/write-zh-bilingual.mddoc1,498 bytesreferences/write-zh-release-notes.mddoc2,368 bytesreferences/write-zh.mddoc55,014 bytesscripts/check-punctuation.shruns151 bytesscripts/check_punctuation.pyruns19,323 bytes
Read SKILL.md
# Write: Cut the AI Taste
Prefix your first line with 🥷 inline, not as its own paragraph.
Strip AI patterns from prose and rewrite it to sound human. Do not improve vocabulary; remove the performance of improvement.
## Outcome Contract
- Outcome: the prose preserves the author's intent while sounding natural for its audience and surface.
- Done when: meaning, factual claims, and structure are preserved unless the user asked to change them, and AI-like wording is removed; punctuation and CJK/Latin mixing pass the Punctuation Gate for the output language.
- Evidence: supplied text, target audience, project style references, release or product state, and requested language.
- Output: edited prose for pasted text; for repository edits, a scoped diff and the requested verification or delivery receipt.
## Durable Context PreflightSkills included
- check
- health
- hunt
- learn
- read
- think
- ui
- write
- check
- health
- hunt
- learn
- read
- think
- ui
- write
Repository facts
- License
- MIT
- Created
- Mar 12, 2026
- Last pushed
- Nov 2, 2026
- Forks
- 432
- Open issues
- 0
- Project activity
- Active
Rank over the last 12 weeks
Now #195 · best #156 · down 9 in 30 days
- #190 on Oct 29
- #191 on Oct 30
- #193 on Oct 31
- #192 from Nov 1 to Nov 2
- #194 on Nov 3
- #195 since Nov 4
61 earlier periods
- #153 on Aug 2
- #153 from Aug 7 to Aug 9
- #156 on Aug 10
- #157 from Aug 11 to Aug 12
- #159 from Aug 13 to Aug 14
- #158 from Aug 15 to Aug 17
- #159 from Aug 18 to Aug 21
- #156 on Aug 22
- #161 from Aug 23 to Aug 24
- #160 on Aug 25
- #161 on Aug 26
- #162 on Aug 27
- #161 on Aug 28
- #162 on Aug 29
- #161 on Aug 30
- #162 on Aug 31
- #165 on Sep 1
- #162 on Sep 2
- #167 on Sep 3
- #165 on Sep 4
- #167 on Sep 5
- #165 on Sep 6
- #167 on Sep 7
- #168 on Sep 8
- #169 from Sep 9 to Sep 10
- #166 on Sep 11
- #171 from Sep 12 to Sep 14
- #173 on Sep 15
- #172 from Sep 16 to Sep 17
- #174 on Sep 18
- #172 on Sep 19
- #176 from Sep 20 to Sep 21
- #177 on Sep 22
- #180 on Sep 23
- #179 on Sep 24
- #181 from Sep 25 to Sep 26
- #182 on Sep 27
- #183 on Sep 28
- #182 on Sep 30
- #185 on Oct 1
- #187 on Oct 2
- #184 on Oct 3
- #182 on Oct 4
- #185 from Oct 5 to Oct 6
- #187 on Oct 7
- #186 on Oct 8
- #188 on Oct 9
- #184 from Oct 10 to Oct 11
- #186 on Oct 12
- #188 on Oct 13
- #187 from Oct 14 to Oct 15
- #186 on Oct 16
- #188 on Oct 17
- #189 on Oct 18
- #188 on Oct 19
- #187 on Oct 20
- #189 from Oct 21 to Oct 22
- #188 on Oct 23
- #189 on Oct 24
- #191 on Oct 25
- #194 on Oct 28
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 81 notes
.claude-plugin/marketplace.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/check/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/health/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/hunt/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/hunt/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/learn/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/learn/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/learn/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/learn/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/waza/skills/learn/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 6 dangerous shell commandsin 6 files: health/SKILL.md:187 health/agents/inspector-control.md:19 read/scripts/fetch.sh:40 and 3 more
- 113 network referencesin 19 files: .claude-plugin/marketplace.json:1 read/scripts/fetch_feishu.py:4 read/scripts/fetch_feishu.py:4 and 16 more
- 2 obfuscation signalsin 2 files: health/scripts/scan_skill_security.py:89 health/scripts/scan_skill_security.py:89
- 2 instruction override signalsin 2 files: health/SKILL.md:123 health/SKILL.md:123
- 50 executable scriptsin 50 files: check/scripts/audit_signals.py:1 check/scripts/incident_ledger.py:1 check/scripts/release_gate.py:1 and 47 more
- 80 references to secretsin 18 files: health/scripts/collect-data.sh:199 health/scripts/collect-data.sh:199 health/scripts/check_agent_context.py:68 and 15 more
- No requests to vote in Hot
Show all 253 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 14
"category": "development", "source": "./", "homepage": "https://github.com/tw93/Waza" - Network accessline 15
"source": "./", "homepage": "https://github.com/tw93/Waza" }, - Network accessline 16
"homepage": "https://github.com/tw93/Waza" - Network accessline 22
"category": "development", "source": "./skills/check", "homepage": "https://github.com/tw93/Waza", - Network accessline 23
"source": "./skills/check", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 24
"homepage": "https://github.com/tw93/Waza", - Network accessline 34
"category": "development", "source": "./skills/health", "homepage": "https://github.com/tw93/Waza", - Network accessline 35
"source": "./skills/health", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 36
"homepage": "https://github.com/tw93/Waza", - Network accessline 46
"category": "development", "source": "./skills/hunt", "homepage": "https://github.com/tw93/Waza", - Network accessline 47
"source": "./skills/hunt", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 48
"homepage": "https://github.com/tw93/Waza", - Network accessline 58
"category": "development", "source": "./skills/learn", "homepage": "https://github.com/tw93/Waza", - Network accessline 59
"source": "./skills/learn", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 60
"homepage": "https://github.com/tw93/Waza", - Network accessline 70
"category": "development", "source": "./skills/read", "homepage": "https://github.com/tw93/Waza", - Network accessline 71
"source": "./skills/read", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 72
"homepage": "https://github.com/tw93/Waza", - Network accessline 82
"category": "development", "source": "./skills/think", "homepage": "https://github.com/tw93/Waza", - Network accessline 83
"source": "./skills/think", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 84
"homepage": "https://github.com/tw93/Waza", - Network accessline 94
"category": "development", "source": "./skills/ui", "homepage": "https://github.com/tw93/Waza", - Network accessline 95
"source": "./skills/ui", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 96
"homepage": "https://github.com/tw93/Waza", - Network accessline 106
"category": "development", "source": "./skills/write", "homepage": "https://github.com/tw93/Waza", - Network accessline 107
"source": "./skills/write", "homepage": "https://github.com/tw93/Waza", "skills": [ - Network accessline 108
"homepage": "https://github.com/tw93/Waza",
plugins/waza/skills/check/references/review-patterns.md
- Network accessline 31
When a diff writes to a path the user already has (`curl -o`, `>`, `tee`, open-truncate-write), ask what survives a failure partway through. Truncating the destination first means a dropped connection, timeout, or non-zero exit leaves a cor
plugins/waza/skills/check/scripts/audit_signals.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/check/scripts/incident_ledger.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/check/scripts/release_gate.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/check/scripts/run-tests.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/waza/skills/health/SKILL.md
- Instruction override signalline 123
**Environment override surface.** Treat the following as attack surface, report when set in tracked files or shipped settings without a justification comment: API base-URL overrides (redirect all traffic to a third party), auto-trust flags - Dangerous shell operationline 187
Action: `git rm --cached .claude/settings.local.json && echo '.claude/settings.local.json' >> .gitignore`
plugins/waza/skills/health/agents/inspector-control.md
- Dangerous shell operationline 19
- Flag genuinely dangerous operations only: sudo *, force-delete root paths, *>* and git push --force origin main
plugins/waza/skills/health/scripts/block-pipe-to-shell.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/health/scripts/check-agent-context.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/waza/skills/health/scripts/check-doc-refs.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/waza/skills/health/scripts/check-maintainability.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/waza/skills/health/scripts/check-verifier-output.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/waza/skills/health/scripts/check_agent_context.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 68
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 1300
[Credential-related source omitted] - Access to secretsline 1308
[Credential-related source omitted] - Access to secretsline 1342
[Credential-related source omitted] - Access to secretsline 1569
[Credential-related source omitted]
plugins/waza/skills/health/scripts/check_doc_refs.py
plugins/waza/skills/health/scripts/check_maintainability.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/health/scripts/check_verifier_output.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/health/scripts/collect-data.sh
- Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 199
[Credential-related source omitted] - Access to secretsline 550
[Credential-related source omitted] - Access to secretsline 551
[Credential-related source omitted] - Access to secretsline 645
[Credential-related source omitted] - Access to secretsline 650
[Credential-related source omitted] - Access to secretsline 785
[Credential-related source omitted] - Access to secretsline 790
[Credential-related source omitted] - Access to secretsline 793
[Credential-related source omitted] - Access to secretsline 805
[Credential-related source omitted] - Access to secretsline 808
[Credential-related source omitted] - Access to secretsline 1026
[Credential-related source omitted] - Access to secretsline 1027
[Credential-related source omitted] - Access to secretsline 1045
[Credential-related source omitted]
plugins/waza/skills/health/scripts/conversation_audit.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/health/scripts/read_skill_description.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/waza/skills/health/scripts/run-health.ps1
- Executable scriptline 1
Executable file
plugins/waza/skills/health/scripts/scan_skill_security.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Possible obfuscationline 89
CONTROL_RE = re.compile(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f]") - Access to secretsline 136
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 150
[Credential-related source omitted]
plugins/waza/skills/read/SKILL.md
- Access to secretsline 47
[Credential-related source omitted]
plugins/waza/skills/read/references/read-methods.md
- Access to secretsline 39
[Credential-related source omitted] - Network accessline 55
# Raw file content (fastest) curl -sL "https://raw.githubusercontent.com/{user}/{repo}/{branch}/{path}" - Network accessline 56
curl -sL "https://raw.githubusercontent.com/{user}/{repo}/{branch}/{path}" - Network accessline 71
READ_PDF_DIR=$(mktemp -d) curl -fL "{pdf_url}" -o "$READ_PDF_DIR/input.pdf" - Network accessline 72
curl -fL "{pdf_url}" -o "$READ_PDF_DIR/input.pdf" - Access to secretsline 106
[Credential-related source omitted]
plugins/waza/skills/read/scripts/deepseek.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 5
[Credential-related source omitted] - Network accessline 23
API = "https://api.deepseek.com/v1/tools/" - Network accessline 32
def call(endpoint, body, key): req = urllib.request.Request( - Network accessline 33
req = urllib.request.Request( - Network accessline 36
[Credential-related source omitted] - Network accessline 37
) with urllib.request.urlopen(req, timeout=TIMEOUT) as resp: return json.loads(resp.read()) - Network accessline 38
with urllib.request.urlopen(req, timeout=TIMEOUT) as resp: - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted]
plugins/waza/skills/read/scripts/fetch.sh
- Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 10
[Credential-related source omitted] - Network accessline 19
# Special thanks to joeseesun for the qiaomu-markdown-proxy project, which # inspired the proxy cascade design: # https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 20
# inspired the proxy cascade design: # https://github.com/joeseesun/qiaomu-markdown-proxy # - Network accessline 21
# https://github.com/joeseesun/qiaomu-markdown-proxy - Dangerous shell operationline 40
trap 'rm -f "$LOCAL_ERR"' EXIT - Network accessline 43
_curl() { if [ -n "$PROXY" ]; then https_proxy="$PROXY" http_proxy="$PROXY" curl -sfL --connect-timeout 10 --max-time 30 "$@" - Network accessline 44
if [ -n "$PROXY" ]; then https_proxy="$PROXY" http_proxy="$PROXY" curl -sfL --connect-timeout 10 --max-time 30 "$@" else - Network accessline 45
https_proxy="$PROXY" http_proxy="$PROXY" curl -sfL --connect-timeout 10 --max-time 30 "$@" - Network accessline 46
else curl -sfL --connect-timeout 10 --max-time 30 "$@" fi - Network accessline 47
curl -sfL --connect-timeout 10 --max-time 30 "$@" - Access to secretsline 90
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Network accessline 102
if OUT=$(_with_retry _curl "https://defuddle.md/$URL"); then echo "[fetch] tier=defuddle status=ok" >&2 - Network accessline 110
if OUT=$(_with_retry _curl "https://r.jina.ai/$URL"); then echo "[fetch] tier=jina status=ok" >&2
plugins/waza/skills/read/scripts/fetch_feishu.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 4
Special thanks to joeseesun for the excellent qiaomu-markdown-proxy project, which inspired the Feishu API integration and document parsing approach here. https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 6
https://github.com/joeseesun/qiaomu-markdown-proxy - Access to secretsline 13
[Credential-related source omitted] - Network accessline 37
API = "https://open.feishu.cn/open-apis" - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 52
[Credential-related source omitted] - Network accessline 58
if missing: return None, "; ".join(missing) + f". {LARK_CLI_HINT}" resp = requests.post(f"{API}/auth/v3/tenant_access_token/internal", - Network accessline 59
[Credential-related source omitted] - Network accessline 60
[Credential-related source omitted] - Access to secretsline 60
[Credential-related source omitted] - Access to secretsline 66
[Credential-related source omitted] - Network accessline 85
def resolve_wiki(token, wiki_token): resp = requests.get(f"{API}/wiki/v2/spaces/get_node", - Network accessline 86
resp = requests.get(f"{API}/wiki/v2/spaces/get_node", - Network accessline 101
[Credential-related source omitted] - Network accessline 102
[Credential-related source omitted] - Network accessline 103
resp = requests.get(f"{API}/docx/v1/documents/{doc_id}/blocks", - Network accessline 223
info_resp = requests.get(f"{API}/docx/v1/documents/{doc_id}",
plugins/waza/skills/read/scripts/fetch_local.py
plugins/waza/skills/read/scripts/fetch_weixin.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 4
Special thanks to joeseesun for the excellent qiaomu-markdown-proxy project, which inspired the Playwright-based WeChat scraping approach in this script. https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 6
https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 26
async def fetch(url: str) -> dict: - Network accessline 103
result = asyncio.run(fetch(sys.argv[1]))
plugins/waza/skills/ui/references/design-reference.md
- Network accessline 280
*Rules in Reflex Fonts, Font Selection, OKLCH, Theme Matrix, Absolute Bans, the motion rules, and the AI Slop Test adapted from [pbakaus/impeccable](https://github.com/pbakaus/impeccable) (Apache 2.0). DESIGN.md Scaffold adapted from [getde
plugins/waza/skills/write/references/write-technical.md
- Network accessline 38
This is an original adaptation informed by [asd-ste100-skill's writing-rule summary](https://github.com/danyuchn/asd-ste100-skill/blob/master/references/writing-rules.md) and its [scope and preservation guidance](https://github.com/danyuchn - Network accessline 40
When explicitly asked to assess compliance with a writing standard, consult its primary text at the applicable version and identify that version in the assessment. Report the requirements actually checked and any coverage gaps. Partial chec
plugins/waza/skills/write/scripts/check-punctuation.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/waza/skills/write/scripts/check_punctuation.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/check/references/review-patterns.md
- Network accessline 31
When a diff writes to a path the user already has (`curl -o`, `>`, `tee`, open-truncate-write), ask what survives a failure partway through. Truncating the destination first means a dropped connection, timeout, or non-zero exit leaves a cor
skills/check/scripts/audit_signals.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/check/scripts/incident_ledger.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/check/scripts/release_gate.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/check/scripts/run-tests.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/health/SKILL.md
- Instruction override signalline 123
**Environment override surface.** Treat the following as attack surface, report when set in tracked files or shipped settings without a justification comment: API base-URL overrides (redirect all traffic to a third party), auto-trust flags - Dangerous shell operationline 187
Action: `git rm --cached .claude/settings.local.json && echo '.claude/settings.local.json' >> .gitignore`
skills/health/agents/inspector-control.md
- Dangerous shell operationline 19
- Flag genuinely dangerous operations only: sudo *, force-delete root paths, *>* and git push --force origin main
skills/health/scripts/block-pipe-to-shell.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/health/scripts/check-agent-context.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/health/scripts/check-doc-refs.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/health/scripts/check-maintainability.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/health/scripts/check-verifier-output.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/health/scripts/check_agent_context.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 68
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Access to secretsline 81
[Credential-related source omitted] - Access to secretsline 1300
[Credential-related source omitted] - Access to secretsline 1308
[Credential-related source omitted] - Access to secretsline 1342
[Credential-related source omitted] - Access to secretsline 1569
[Credential-related source omitted]
skills/health/scripts/check_doc_refs.py
skills/health/scripts/check_maintainability.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/health/scripts/check_verifier_output.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/health/scripts/collect-data.sh
- Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 199
[Credential-related source omitted] - Access to secretsline 550
[Credential-related source omitted] - Access to secretsline 551
[Credential-related source omitted] - Access to secretsline 645
[Credential-related source omitted] - Access to secretsline 650
[Credential-related source omitted] - Access to secretsline 785
[Credential-related source omitted] - Access to secretsline 790
[Credential-related source omitted] - Access to secretsline 793
[Credential-related source omitted] - Access to secretsline 805
[Credential-related source omitted] - Access to secretsline 808
[Credential-related source omitted] - Access to secretsline 1026
[Credential-related source omitted] - Access to secretsline 1027
[Credential-related source omitted] - Access to secretsline 1045
[Credential-related source omitted]
skills/health/scripts/conversation_audit.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/health/scripts/read_skill_description.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/health/scripts/run-health.ps1
- Executable scriptline 1
Executable file
skills/health/scripts/scan_skill_security.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Possible obfuscationline 89
CONTROL_RE = re.compile(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f-\x9f]") - Access to secretsline 136
[Credential-related source omitted] - Access to secretsline 137
[Credential-related source omitted] - Access to secretsline 150
[Credential-related source omitted]
skills/read/SKILL.md
- Access to secretsline 47
[Credential-related source omitted]
skills/read/references/read-methods.md
- Access to secretsline 39
[Credential-related source omitted] - Network accessline 55
# Raw file content (fastest) curl -sL "https://raw.githubusercontent.com/{user}/{repo}/{branch}/{path}" - Network accessline 56
curl -sL "https://raw.githubusercontent.com/{user}/{repo}/{branch}/{path}" - Network accessline 71
READ_PDF_DIR=$(mktemp -d) curl -fL "{pdf_url}" -o "$READ_PDF_DIR/input.pdf" - Network accessline 72
curl -fL "{pdf_url}" -o "$READ_PDF_DIR/input.pdf" - Access to secretsline 106
[Credential-related source omitted]
skills/read/scripts/deepseek.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 5
[Credential-related source omitted] - Network accessline 23
API = "https://api.deepseek.com/v1/tools/" - Network accessline 32
def call(endpoint, body, key): req = urllib.request.Request( - Network accessline 33
req = urllib.request.Request( - Network accessline 36
[Credential-related source omitted] - Network accessline 37
) with urllib.request.urlopen(req, timeout=TIMEOUT) as resp: return json.loads(resp.read()) - Network accessline 38
with urllib.request.urlopen(req, timeout=TIMEOUT) as resp: - Access to secretsline 91
[Credential-related source omitted] - Access to secretsline 93
[Credential-related source omitted]
skills/read/scripts/fetch.sh
- Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 10
[Credential-related source omitted] - Network accessline 19
# Special thanks to joeseesun for the qiaomu-markdown-proxy project, which # inspired the proxy cascade design: # https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 20
# inspired the proxy cascade design: # https://github.com/joeseesun/qiaomu-markdown-proxy # - Network accessline 21
# https://github.com/joeseesun/qiaomu-markdown-proxy - Dangerous shell operationline 40
trap 'rm -f "$LOCAL_ERR"' EXIT - Network accessline 43
_curl() { if [ -n "$PROXY" ]; then https_proxy="$PROXY" http_proxy="$PROXY" curl -sfL --connect-timeout 10 --max-time 30 "$@" - Network accessline 44
if [ -n "$PROXY" ]; then https_proxy="$PROXY" http_proxy="$PROXY" curl -sfL --connect-timeout 10 --max-time 30 "$@" else - Network accessline 45
https_proxy="$PROXY" http_proxy="$PROXY" curl -sfL --connect-timeout 10 --max-time 30 "$@" - Network accessline 46
else curl -sfL --connect-timeout 10 --max-time 30 "$@" fi - Network accessline 47
curl -sfL --connect-timeout 10 --max-time 30 "$@" - Access to secretsline 90
[Credential-related source omitted] - Access to secretsline 92
[Credential-related source omitted] - Network accessline 102
if OUT=$(_with_retry _curl "https://defuddle.md/$URL"); then echo "[fetch] tier=defuddle status=ok" >&2 - Network accessline 110
if OUT=$(_with_retry _curl "https://r.jina.ai/$URL"); then echo "[fetch] tier=jina status=ok" >&2
skills/read/scripts/fetch_feishu.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 4
Special thanks to joeseesun for the excellent qiaomu-markdown-proxy project, which inspired the Feishu API integration and document parsing approach here. https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 6
https://github.com/joeseesun/qiaomu-markdown-proxy - Access to secretsline 13
[Credential-related source omitted] - Network accessline 37
API = "https://open.feishu.cn/open-apis" - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 52
[Credential-related source omitted] - Network accessline 58
if missing: return None, "; ".join(missing) + f". {LARK_CLI_HINT}" resp = requests.post(f"{API}/auth/v3/tenant_access_token/internal", - Network accessline 59
[Credential-related source omitted] - Network accessline 60
[Credential-related source omitted] - Access to secretsline 60
[Credential-related source omitted] - Access to secretsline 66
[Credential-related source omitted] - Network accessline 85
def resolve_wiki(token, wiki_token): resp = requests.get(f"{API}/wiki/v2/spaces/get_node", - Network accessline 86
resp = requests.get(f"{API}/wiki/v2/spaces/get_node", - Network accessline 101
[Credential-related source omitted] - Network accessline 102
[Credential-related source omitted] - Network accessline 103
resp = requests.get(f"{API}/docx/v1/documents/{doc_id}/blocks", - Network accessline 223
info_resp = requests.get(f"{API}/docx/v1/documents/{doc_id}",
skills/read/scripts/fetch_local.py
skills/read/scripts/fetch_weixin.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 4
Special thanks to joeseesun for the excellent qiaomu-markdown-proxy project, which inspired the Playwright-based WeChat scraping approach in this script. https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 6
https://github.com/joeseesun/qiaomu-markdown-proxy - Network accessline 26
async def fetch(url: str) -> dict: - Network accessline 103
result = asyncio.run(fetch(sys.argv[1]))
skills/ui/references/design-reference.md
- Network accessline 280
*Rules in Reflex Fonts, Font Selection, OKLCH, Theme Matrix, Absolute Bans, the motion rules, and the AI Slop Test adapted from [pbakaus/impeccable](https://github.com/pbakaus/impeccable) (Apache 2.0). DESIGN.md Scaffold adapted from [getde
skills/write/references/write-technical.md
- Network accessline 38
This is an original adaptation informed by [asd-ste100-skill's writing-rule summary](https://github.com/danyuchn/asd-ste100-skill/blob/master/references/writing-rules.md) and its [scope and preservation guidance](https://github.com/danyuchn - Network accessline 40
When explicitly asked to assess compliance with a writing standard, consult its primary text at the applicable version and identify that version in the assessment. Report the requirements actually checked and any coverage gaps. Partial chec
skills/write/scripts/check-punctuation.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/write/scripts/check_punctuation.py
- Executable scriptline 1
#!/usr/bin/env python3
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: 4 facts
- Uses SSH keys, which the skill description does not mentionhealth/scripts/collect-data.sh:645High confidence
- Contacts api.deepseek.com, which SKILL.md, the README and the plugin manifest do not mentionread/scripts/deepseek.py:23High confidence
- Uses SSH keys, which the skill description does not mentionhealth/scripts/collect-data.sh:645High confidence
- Contacts api.deepseek.com, which SKILL.md, the README and the plugin manifest do not mentionread/scripts/deepseek.py:23High confidence
Signal confidence: 224 facts
- Network access in prose of documentationcheck/references/review-patterns.md:31Low confidence
- Executable script in code of a file that runscheck/scripts/audit_signals.py:1High confidence
- Executable script in code of a file that runscheck/scripts/incident_ledger.py:1High confidence
- Executable script in code of a file that runscheck/scripts/release_gate.py:1High confidence
- Executable script in code of a file that runscheck/scripts/run-tests.sh:1High confidence
- Instruction override signal in prose of the SKILL.mdhealth/SKILL.md:123High confidence
- Dangerous shell operation in prose of the SKILL.mdhealth/SKILL.md:187Low confidence
- Dangerous shell operation in prose of documentationhealth/agents/inspector-control.md:19Low confidence
- Executable script in code of a file that runshealth/scripts/block-pipe-to-shell.py:1High confidence
- Executable script in code of a file that runshealth/scripts/check-agent-context.sh:1High confidence
- Executable script in code of a file that runshealth/scripts/check-doc-refs.sh:1High confidence
- Executable script in code of a file that runshealth/scripts/check-maintainability.sh:1High confidence
- Executable script in code of a file that runshealth/scripts/check-verifier-output.sh:1High confidence
- Executable script in code of a file that runshealth/scripts/check_agent_context.py:1High confidence
- Access to secrets in code of a file that runshealth/scripts/check_agent_context.py:68High confidence
- Access to secrets in code of a file that runshealth/scripts/check_agent_context.py:69High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/check_agent_context.py:81Low confidence
- Access to secrets in code of a file that runshealth/scripts/check_agent_context.py:1300High confidence
- Access to secrets in code of a file that runshealth/scripts/check_agent_context.py:1308High confidence
- Access to secrets in code of a file that runshealth/scripts/check_agent_context.py:1342High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/check_agent_context.py:1569Low confidence
- Executable script in code of a file that runshealth/scripts/check_doc_refs.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/check_doc_refs.py:168Low confidence
- Executable script in code of a file that runshealth/scripts/check_maintainability.py:1High confidence
- Executable script in code of a file that runshealth/scripts/check_verifier_output.py:1High confidence
- Executable script in code of a file that runshealth/scripts/collect-data.sh:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:199Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:550Low confidence
- Access to secrets in code of a file that runshealth/scripts/collect-data.sh:551High confidence
- Access to secrets in code of a file that runs: reads a credential storehealth/scripts/collect-data.sh:645High confidence
- Access to secrets in code of a file that runshealth/scripts/collect-data.sh:650High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:785Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:790Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:793Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:805Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:808Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:1026Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:1027Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/collect-data.sh:1045Low confidence
- Executable script in code of a file that runshealth/scripts/conversation_audit.py:1High confidence
- Executable script in code of a file that runshealth/scripts/read_skill_description.py:1High confidence
- Executable script in code of a file that runshealth/scripts/run-health.ps1:1High confidence
- Executable script in code of a file that runshealth/scripts/scan_skill_security.py:1High confidence
- Access to secrets in code of a file that runshealth/scripts/scan_skill_security.py:53High confidence
- Access to secrets in code of a file that runshealth/scripts/scan_skill_security.py:54High confidence
- Possible obfuscation in code of a file that runshealth/scripts/scan_skill_security.py:89High confidence
- Access to secrets in code of a file that runshealth/scripts/scan_skill_security.py:136High confidence
- Access to secrets in code of a file that runshealth/scripts/scan_skill_security.py:137High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuehealth/scripts/scan_skill_security.py:150Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueread/SKILL.md:47Low confidence
and 174 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/waza/skills/check/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/waza/skills/check/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/waza/skills/check/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/waza/skills/check/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/tw93-waza/)