#132 by GitHub stars
HKUSTDial/Supervisor-Skills
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿,你的 AI 科研副导师。
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/benchmark-paper-template/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/deep-research/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/drawio-reconstruction/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/figure-designer/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/idea-evaluator/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/intro-drafter/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/paper-polish/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/paper-writer/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/pre-submission-reviewer/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/rebuttal-guidance/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/tech-paper-template/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/vibe-research-workflow/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
a20d76ef3979 → a20d76ef3979
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Heat
7.8- Star growth, last 7 daysAhead of 97% of tracked repositories
- Star growth, last 24 hoursAhead of 97% of tracked repositories
- Rank movement, last 7 daysAhead of 84% of tracked repositories
- Commits, last 30 daysAhead of 64% 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
- benchmark-paper-template
skills/benchmark-paper-template - deep-research
skills/deep-research - drawio-reconstruction
skills/drawio-reconstruction - figure-designer
skills/figure-designer - idea-evaluator
skills/idea-evaluator - intro-drafter
skills/intro-drafter - paper-polish
skills/paper-polish - paper-writer
skills/paper-writer - pre-submission-reviewer
skills/pre-submission-reviewer - rebuttal-guidance
skills/rebuttal-guidance - tech-paper-template
skills/tech-paper-template - vibe-research-workflow
skills/vibe-research-workflow
How it works
benchmark-paper-template
When your agent uses it
Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when writing a benchmark paper, structuring a benchmark paper, checking whether a benchmark idea is substantive, drafting a benchmark Introduction, or planning the data-construction pipeline or experiments.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
2,365 tokensWhen the skill is activated
Reference documents
12,536 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Core capabilities
- Benchmark paper vs technical paper
- The five pillars
- Introduction six-part flowchart
- Section skeleton
- Prompt template
- Reference exemplars
- Usage tips
- References
Files
SKILL.mdcore11,184 bytesSKILL.mdcore11,184 bytesreferences/benchmark-design.mddoc7,558 bytesreferences/checklist.mddoc6,934 bytesreferences/construction-pipeline.mddoc6,357 bytesreferences/experiments.mddoc8,218 bytesreferences/gap-analysis.mddoc5,467 bytesreferences/instantiation-template.mddoc5,327 bytesreferences/orchestrator-notes.mddoc5,263 bytesreferences/paper-structure.mddoc9,906 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdeep-research
When your agent uses it
Runs a deep, survey-grade literature investigation on a research topic: freezes research questions, searches from multiple adversarial perspectives, verifies every citation, synthesizes evidence into a MECE taxonomy with in-sentence cross-comparison, and answers the research questions in an evidence-first report. Use when the user asks for a literature review, a survey of a field, research landscape mapping, or a deep dive into what is known about a topic.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
2,032 tokensWhen the skill is activated
Reference documents
5,113 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use this skill
- When NOT to use this skill
- Capability check
- Step 0: freeze the research brief
- Phase 1: scout (search and verify)
- Phase 2: synthesize
- The six gates and the iteration loop
- Presentation
- Cross-discipline evidence standards
- Unconfirmed markers: a deliberate difference from paper prose
- Output language
- Delivery
- Boundaries with sibling skills
Files
SKILL.mdcore9,428 bytesreferences/citation-protocol.mddoc2,107 bytesreferences/hedge-calibration.mddoc2,009 bytesreferences/output-structure.mddoc5,938 bytesreferences/quality-gates.mddoc3,563 bytesreferences/search-strategy.mddoc2,161 bytesreferences/self-adversarial.mddoc2,417 bytesreferences/synthesis-framework.mddoc4,709 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdrawio-reconstruction
When your agent uses it
Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure, architecture diagram, slide, UI screenshot, or image folder turned into `.drawio` XML; batch requests use a manifest with bounded parallelism when available and a full-fidelity serial fallback otherwise.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
4,391 tokensWhen the skill is activated
Reference documents
4,549 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Helper Script Location
- Fidelity Contract
- Batch Folder Workflow
- Mandatory Reference Inventory
- Reconstruction Strategy
- Medium Decision Rules
- Icon Reconstruction Discipline
- Screenshot Crop Rules
- Curves And Arrows
- Typography And Layout
- Default Workflow
- Mandatory Visual Audit
- Using A User-Approved Reference Diagram
- Redline Feedback
- Verification
- Final Response
Scripts executed separately
scripts/batch_manifest.pyscripts/batch_verify.pyscripts/check_drawio.pyscripts/crop_assist.pyscripts/export_drawio.py
Files
.gitignoreasset262 bytesLICENSEasset1,074 bytesREADME.mddoc8,964 bytesREADME.zh-CN.mddoc8,623 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesSKILL.mdcore21,671 bytesagents/openai.yamlasset302 bytesassets/cases/data_lake_drawio.pngasset492,829 bytesassets/cases/data_lake_original.pngasset1,289,583 bytesassets/cases/data_man_drawio.pngasset651,847 bytesassets/cases/data_man_original.pngasset1,875,717 bytesassets/cases/data_sci2_drawio.pngasset778,923 bytesassets/cases/data_sci2_original.pngasset1,799,262 bytesexamples/data_lake.drawioasset380,343 bytesexamples/data_lake.pngasset1,289,583 bytesexamples/data_man.drawioasset490,095 bytesexamples/data_man.pngasset1,875,717 bytesexamples/data_sci2.drawioasset416,876 bytesexamples/data_sci2.pngasset1,799,262 bytesrequirements.txtdoc13 bytesscripts/batch_manifest.pyruns4,172 bytesscripts/batch_verify.pyruns2,853 bytesscripts/check_drawio.pyruns11,872 bytesscripts/crop_assist.pyruns13,347 bytesscripts/export_drawio.pyruns3,378 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfigure-designer
When your agent uses it
Advises on the design of the three core figures in a technical paper: the Motivated Example (Figure 1), the Solution Overview (Methodology), and the Experimental Results figures. Recommends the right design paradigm, layout, labelling, and tool for each figure type, then runs a quality-control audit. Use when the user asks to 'design a figure', 'draw Figure 1', 'plot experiment results', 'choose the right chart type', 'which figure tool to use', or 'figure looks unprofessional'.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
1,771 tokensWhen the skill is activated
Reference documents
5,152 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use this skill
- When NOT to use this skill
- Core procedure
- Integrity gate
- Output format
Files
SKILL.mdcore7,454 bytesreferences/design-rules.mddoc3,979 bytesreferences/experimental-results.mddoc5,117 bytesreferences/motivated-example.mddoc4,618 bytesreferences/solution-overview.mddoc4,893 bytesreferences/tools.mddoc3,957 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubidea-evaluator
When your agent uses it
Evaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader) plus idea-lifecycle and student-capability matching, paradigm-shift probing, and a fatal-flaws audit. Returns a reviewer-style verdict; non-STEM ideas route to substitute frameworks. Use when the user has a draft research idea and asks whether it is worth pursuing, asks to 'evaluate this idea', 'score this idea', 'assess feasibility', 'novelty check', 'is this a good research direction', or before committing to a paper scope.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
3,078 tokensWhen the skill is activated
Reference documents
17,274 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use this skill
- When NOT to use this skill
- Core procedure
- Integrity gate
- Output format
Files
SKILL.mdcore13,597 bytesreferences/domain-evaluation-frameworks.mddoc8,951 bytesreferences/fatal-flaws.mddoc8,659 bytesreferences/five-dimensions.mddoc12,621 bytesreferences/lifecycle-capability-matching.mddoc7,731 bytesreferences/paradigm-elephant.mddoc4,715 bytesreferences/paradigm-examples.mddoc4,976 bytesreferences/paradigm-first-principles.mddoc4,694 bytesreferences/paradigm-hamming.mddoc4,834 bytesreferences/paradigm-shift-probe.mddoc6,290 bytesreferences/paradigm-technology-cycle.mddoc4,820 bytesreferences/worked-examples.mddoc8,411 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubintro-drafter
When your agent uses it
Drafts the Introduction prose for a technical paper, guided internally by a six-paragraph flowchart: background and running example, existing limitations, problem essence and goal, key challenges, solution overview, contributions. Positions the paper as Technique or New Problem/Setting, aligns contributions with challenges, and weaves verified citations. Outputs flowing prose by default, or an outline on request. Use when the user asks to draft, outline, or restructure an Introduction.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
2,134 tokensWhen the skill is activated
Reference documents
9,079 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Evidence rules (inherited)
- When to use this skill
- When NOT to use this skill
- Pre-check: STEM or not
- Core procedure (STEM)
- What the user receives
- Outline mode (on explicit request)
- Tone references
- Cross-skill handoffs
- Output language
Files
SKILL.mdcore9,699 bytesSKILL.mdcore9,699 bytesreferences/contribution-patterns.mddoc4,352 bytesreferences/evidence-discipline.mddoc7,858 bytesreferences/flowchart.mddoc6,914 bytesreferences/paper-types.mddoc5,769 bytesreferences/prose-delivery.mddoc3,011 bytesreferences/running-example.mddoc5,091 bytesreferences/worked-examples.mddoc7,365 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpaper-polish
When your agent uses it
Polishes existing academic prose while preserving the author's meaning: grammar and flow repair, tone calibration against evidence strength, AI-tone removal, and Chinese-to-English rewriting at submission quality. Never fabricates data, citations, or claims, and flags any edit that could change scientific meaning. Use when the user asks to polish a draft, fix awkward wording, remove AI flavor, translate a Chinese manuscript into publishable English, or tone down overclaiming.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
2,671 tokensWhen the skill is activated
Reference documents
2,969 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use this skill
- When NOT to use this skill
- The overriding rule: stay faithful to the author's meaning
- Never fabricate content
- Conservative by default
- One polishing pass
- Polish by section conventions
- Calibration: do not let the author overclaim
- Be fair to prior work
- Removing AI tone
- Rewriting Chinese drafts into English
- Working on files versus pasted text
- Long documents
- Content you cannot read
- How to deliver
- When the problem is deeper than language
- Output language
Files
SKILL.mdcore12,311 bytesSKILL.mdcore12,311 bytesSKILL.mdcore12,311 bytesreferences/academic-phrasebank.mddoc4,559 bytesreferences/ai-tone-guardrails.mddoc4,512 bytesreferences/section-conventions.mddoc4,395 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpaper-writer
When your agent uses it
Drafts publishable paper prose from the author's own materials, from a single paragraph to a full manuscript, across STEM and non-STEM fields. Every factual claim traces to user input, verified retrieval, or field common knowledge; citations pass an independent verification ladder; delivery is clean prose with zero placeholder tags. Use when the user asks to write a section, turn an idea or results into paper text, or draft a full paper.
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
3,047 tokensWhen the skill is activated
Reference documents
10,434 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Hard rules
- When to use this skill
- When NOT to use this skill
- Capability check (run once per session)
- Workflow
- Proactive literature searching
- Citations and references
- Output language
- Boundaries with sibling skills
Files
SKILL.mdcore14,013 bytesSKILL.mdcore14,013 bytesSKILL.mdcore14,013 bytesSKILL.mdcore14,013 bytesSKILL.mdcore14,013 bytesSKILL.mdcore14,013 bytesreferences/academic-phrasebank.mddoc4,548 bytesreferences/ai-tone-guardrails.mddoc4,500 bytesreferences/citation-style.mddoc4,804 bytesreferences/evidence-discipline.mddoc7,869 bytesreferences/prose-delivery.mddoc3,027 bytesreferences/section-conventions.mddoc4,384 bytesreferences/section-guidance.mddoc4,912 bytesreferences/verification-checklist.mddoc5,166 bytesreferences/verification-ladder.mddoc6,893 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpre-submission-reviewer
When your agent uses it
Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy (CRITICAL / MAJOR / MINOR) and flags banned AI-tone vocabulary and em-dash misuse. Use when the user asks to 'review this paper', 'audit before submission', 'check the draft', 'find issues', 'proofread', or within one week of a submission deadline.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
2,854 tokensWhen the skill is activated
Reference documents
5,459 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use this skill
- When NOT to use this skill
- Core procedure
- Severity taxonomy
- Integrity gate
- Output format
Files
SKILL.mdcore12,686 bytesSKILL.mdcore12,686 bytesreferences/forbidden-patterns.mddoc4,801 bytesreferences/grammar-rules.mddoc4,767 bytesreferences/latex-rules.mddoc4,439 bytesreferences/logic-and-structure.mddoc4,663 bytesreferences/section-guides.mddoc5,334 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubrebuttal-guidance
When your agent uses it
Provides actionable peer-review rebuttal guidance (not full rebuttal prose) using conditional persuasion P(Z|X,Y): match reviewer mindset X, recommend strategy Y, optionally ground in manuscript evidence and similar successful historical (review, rebuttal) pairs. Use when the user pastes reviewer comments, asks for rebuttal help, rebuttal guidance, response to reviewers, how to reply to R1.W2, OpenReview rebuttal, or the reviewer ignored the rebuttal.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
1,270 tokensWhen the skill is activated
Reference documents
8,996 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use
- When NOT to use
- Core procedure
- Reference map
Files
SKILL.mdcore5,307 bytesreferences/checklist.mddoc1,944 bytesreferences/concern-classification.mddoc2,260 bytesreferences/mindset-library.mddoc17,314 bytesreferences/mindset-matching-heuristics.mddoc2,571 bytesreferences/response-templates.mddoc2,528 bytesreferences/strategy-dimensions.mddoc2,491 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtech-paper-template
When your agent uses it
Structures a technical paper's full logical skeleton using a thinking-template table (research background, limitations, key idea or goal, challenges, methodology modules, contributions), positions the paper as Technique or New Problem/Setting, and runs a four-point self-consistency check. Use when the user is brainstorming a paper, discussing progress with an advisor, or planning the paper before drafting. Also use for 'paper skeleton', 'paper logic chain', 'thinking template', 'paper-structure planning'.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,616 tokensWhen the skill is activated
Reference documents
4,856 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use this skill
- When NOT to use this skill
- Core procedure
- Integrity gate
- Output format
Files
SKILL.mdcore6,975 bytesreferences/consistency-checks.mddoc5,632 bytesreferences/paper-types.mddoc4,853 bytesreferences/thinking-template.mddoc5,487 bytesreferences/worked-examples.mddoc5,972 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvibe-research-workflow
When your agent uses it
Guides AI-assisted research across three sub-flows, Vibe Coding, Vibe Figure, and Vibe Writing, with behavioural rules that keep the user in charge of academic judgment while delegating mechanical work to AI. Recommends the right tool (Cursor, Claude Code, Codex, Figma, Gemini) for the current stage. Use when the user asks 'how to use AI for research', 'Vibe Coding tips', 'AI-assisted writing workflow', 'which AI tool for this', or starts an AI-assisted work session.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,713 tokensWhen the skill is activated
Reference documents
5,737 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to use this skill
- When NOT to use this skill
- Core procedure
- Integrity gate
- Output format
Files
SKILL.mdcore7,449 bytesreferences/behavior-guidelines.mddoc5,185 bytesreferences/tool-selection.mddoc4,694 bytesreferences/vibe-coding.mddoc4,586 bytesreferences/vibe-figure.mddoc4,159 bytesreferences/vibe-writing.mddoc6,762 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- benchmark-paper-template
- deep-research
- drawio-reconstruction
- figure-designer
- idea-evaluator
- intro-drafter
- paper-polish
- paper-writer
- pre-submission-reviewer
- rebuttal-guidance
- tech-paper-template
- vibe-research-workflow
Repository facts
- License
- No license detected
- Created
- Apr 19, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 698
- Open issues
- 1
- Project activity
- Active
Rank over the last 12 weeks
Now #132 · best #132 · up 23 in 30 days
- #135 on Oct 30
- #134 on Oct 31
- #133 on Nov 1
- #132 on Nov 2
- #133 from Nov 3 to Nov 5
- #132 since Nov 6
64 earlier periods
- #196 on Aug 2
- #192 on Aug 7
- #190 on Aug 8
- #188 on Aug 9
- #190 on Aug 10
- #189 on Aug 11
- #187 on Aug 12
- #190 on Aug 13
- #189 on Aug 14
- #188 on Aug 15
- #189 from Aug 16 to Aug 17
- #192 on Aug 18
- #191 on Aug 19
- #187 from Aug 20 to Aug 21
- #183 on Aug 22
- #188 on Aug 23
- #185 on Aug 24
- #187 from Aug 25 to Aug 26
- #188 on Aug 27
- #186 from Aug 28 to Aug 29
- #182 on Aug 30
- #181 on Aug 31
- #184 on Sep 1
- #176 on Sep 2
- #182 on Sep 3
- #179 from Sep 4 to Sep 5
- #175 on Sep 6
- #176 from Sep 7 to Sep 8
- #177 on Sep 9
- #175 on Sep 10
- #173 on Sep 11
- #174 from Sep 12 to Sep 13
- #172 on Sep 14
- #171 on Sep 15
- #168 on Sep 16
- #167 from Sep 17 to Sep 18
- #165 on Sep 19
- #168 on Sep 20
- #166 from Sep 21 to Sep 23
- #165 on Sep 24
- #164 on Sep 25
- #165 from Sep 26 to Sep 29
- #162 on Sep 30
- #163 from Oct 1 to Oct 2
- #161 on Oct 3
- #158 on Oct 4
- #157 on Oct 5
- #155 on Oct 6
- #157 on Oct 7
- #155 on Oct 8
- #153 from Oct 9 to Oct 10
- #151 on Oct 11
- #149 on Oct 12
- #145 on Oct 13
- #146 on Oct 14
- #143 on Oct 15
- #141 from Oct 16 to Oct 17
- #142 on Oct 18
- #141 on Oct 19
- #140 from Oct 20 to Oct 21
- #139 from Oct 22 to Oct 24
- #140 on Oct 25
- #135 on Oct 28
- #134 on Oct 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Changed on Oct 27, 2026
No longer found: Dangerous shell operation, Possible obfuscation
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 164 notes
skills/benchmark-paper-template/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/drawio-reconstruction/examples/data_lake.drawio:160Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:158Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:159Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:187Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:185Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:186Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:202Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:200Analysis incomplete: physical or joined line exceeds character limitskills/drawio-reconstruction/examples/data_lake.drawio:201Analysis incomplete: physical or joined line exceeds character limit
- No broad tool permissions
- 2 dangerous shell commandsin 2 files: drawio-reconstruction/README.md:115 drawio-reconstruction/README.zh-CN.md:116
- 27 network referencesin 3 files: drawio-reconstruction/README.zh-CN.md:9 drawio-reconstruction/README.md:9 paper-writer/references/citation-style.md:92
- No hidden or obfuscated text
- No instruction overrides
- 5 executable scriptsin 5 files: drawio-reconstruction/scripts/batch_manifest.py:1 drawio-reconstruction/scripts/batch_verify.py:1 drawio-reconstruction/scripts/check_drawio.py:1 and 2 more
- 4 references to secretsin 2 files: drawio-reconstruction/scripts/export_drawio.py:28 drawio-reconstruction/.gitignore:10
- No requests to vote in Hot
Show all 38 signals by file
skills/drawio-reconstruction/.gitignore
- Access to secretsline 10
[Credential-related source omitted]
skills/drawio-reconstruction/README.md
- Network accessline 9
[](https://arxiv.org/abs/2605.15677) - Network accessline 10
[](https://huggingface.co/datasets/sxy1620348809/VCG-Bench) - Network accessline 16
The companion benchmark repository is released at https://github.com/sxy1499894281/VCG-Bench. - Network accessline 85
Use $skill-installer to install https://github.com/HKUSTDial/Supervisor-Skills/tree/main/skills/drawio-reconstruction. - Network accessline 112
Download the matching `.deb` or AppImage from the official [drawio-desktop releases](https://github.com/jgraph/drawio-desktop/releases). For a downloaded `.deb`: - Dangerous shell operationline 115
sudo apt install ./drawio-amd64-*.deb - Network accessline 189
- Homepage: https://sxy1499894281.github.io/VCG-Bench/ - Network accessline 190
- Paper: https://arxiv.org/abs/2605.15677 - Network accessline 191
- Dataset: https://huggingface.co/datasets/sxy1620348809/VCG-Bench - Network accessline 192
- Code: https://github.com/sxy1499894281/VCG-Bench - Network accessline 208
archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2605.15677}, - Network accessline 209
primaryClass={cs.CL}, url={https://arxiv.org/abs/2605.15677}, } - Network accessline 210
url={https://arxiv.org/abs/2605.15677},
skills/drawio-reconstruction/README.zh-CN.md
- Network accessline 9
[](https://arxiv.org/abs/2605.15677) - Network accessline 10
[](https://huggingface.co/datasets/sxy1620348809/VCG-Bench) - Network accessline 16
配套 benchmark 仓库地址: https://github.com/sxy1499894281/VCG-Bench - Network accessline 17
https://github.com/sxy1499894281/VCG-Bench - Network accessline 86
Use $skill-installer to install https://github.com/HKUSTDial/Supervisor-Skills/tree/main/skills/drawio-reconstruction. - Network accessline 113
从官方 [drawio-desktop releases](https://github.com/jgraph/drawio-desktop/releases) 下载匹配平台的 `.deb` 或 AppImage。下载 `.deb` 后可执行: - Dangerous shell operationline 116
sudo apt install ./drawio-amd64-*.deb - Network accessline 190
- Homepage: https://sxy1499894281.github.io/VCG-Bench/ - Network accessline 191
- Paper: https://arxiv.org/abs/2605.15677 - Network accessline 192
- Dataset: https://huggingface.co/datasets/sxy1620348809/VCG-Bench - Network accessline 193
- Code: https://github.com/sxy1499894281/VCG-Bench - Network accessline 209
archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2605.15677}, - Network accessline 210
primaryClass={cs.CL}, url={https://arxiv.org/abs/2605.15677}, } - Network accessline 211
url={https://arxiv.org/abs/2605.15677},
skills/drawio-reconstruction/scripts/batch_manifest.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/drawio-reconstruction/scripts/batch_verify.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/drawio-reconstruction/scripts/check_drawio.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/drawio-reconstruction/scripts/crop_assist.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/drawio-reconstruction/scripts/export_drawio.py
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.
Signal confidence: 37 facts
- Network access in prose of documentationdrawio-reconstruction/README.md:9Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.md:10Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.md:16Low confidence
- Network access in code of documentationdrawio-reconstruction/README.md:85Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.md:112Low confidence
- Dangerous shell operation in code of documentationdrawio-reconstruction/README.md:115Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.md:189Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.md:190Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.md:191Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.md:192Low confidence
- Network access in code of documentationdrawio-reconstruction/README.md:208Low confidence
- Network access in code of documentationdrawio-reconstruction/README.md:209Low confidence
- Network access in code of documentationdrawio-reconstruction/README.md:210Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:9Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:10Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:16Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:17Low confidence
- Network access in code of documentationdrawio-reconstruction/README.zh-CN.md:86Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:113Low confidence
- Dangerous shell operation in code of documentationdrawio-reconstruction/README.zh-CN.md:116Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:190Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:191Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:192Low confidence
- Network access in prose of documentationdrawio-reconstruction/README.zh-CN.md:193Low confidence
- Network access in code of documentationdrawio-reconstruction/README.zh-CN.md:209Low confidence
- Network access in code of documentationdrawio-reconstruction/README.zh-CN.md:210Low confidence
- Network access in code of documentationdrawio-reconstruction/README.zh-CN.md:211Low confidence
- Executable script in code of a file that runsdrawio-reconstruction/scripts/batch_manifest.py:1High confidence
- Executable script in code of a file that runsdrawio-reconstruction/scripts/batch_verify.py:1High confidence
- Executable script in code of a file that runsdrawio-reconstruction/scripts/check_drawio.py:1High confidence
- Executable script in code of a file that runsdrawio-reconstruction/scripts/crop_assist.py:1High confidence
- Executable script in code of a file that runsdrawio-reconstruction/scripts/export_drawio.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuedrawio-reconstruction/scripts/export_drawio.py:28Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuedrawio-reconstruction/scripts/export_drawio.py:31Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuedrawio-reconstruction/scripts/export_drawio.py:38Low confidence
- Network access in code of documentationpaper-writer/references/citation-style.md:92Low confidence
- Network access in code of documentationpaper-writer/references/citation-style.md:93Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/benchmark-paper-template/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/benchmark-paper-template/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/benchmark-paper-template/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/benchmark-paper-template/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/benchmark-paper-template/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/benchmark-paper-template/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/hkustdial-supervisor-skills/)