Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
46,100 skills from 2,198 repositories · updated 1 hour ago
9,541 skills
- concept-diagramsHezaoHezao/poirotMinimal SVG diagrams as standalone HTML files.OtherNo warnings★ 257↓ —
- example-skilltravisjneuman/.claudeExample skill - replace with your skill's description and activation keywordsOtherNo warnings★ 106↓ —
- bootstrapHezaoHezao/poirotOnboarding conversation to generate a user profile.OtherNo warnings★ 257↓ —
- codebase-inspectionHezaoHezao/poirotInspect codebases: LOC, languages, ratios via pygount.OtherNo warnings★ 257↓ —
- github-repo-managementHezaoHezao/poirotClone, create, fork repos; manage remotes, releases.OtherNo warnings★ 257↓ —
- grace-explainerosovv/grace-marketplaceExplain GRACE 4 methodology, .grace artifacts, semantic anchors, change lifecycle, verification, and migration boundaries.OtherNo warnings★ 257↓ —Also in 1 other repo
- grace-setup-subagentsosovv/grace-marketplaceCreate GRACE 4 worker and reviewer subagent presets that understand .grace artifacts, scopes, assertions, and verification evidence.OtherNo warnings★ 257↓ —Also in 1 other repo
- spikeHezaoHezao/poirotThrowaway experiments to validate an idea before build.OtherNo warnings★ 257↓ —
- grace-askosovv/grace-marketplaceAnswer questions about a GRACE 4 project by navigating .grace current-state artifacts and file-local semantic markup.OtherNo warnings★ 257↓ —Also in 1 other repo
- grace-executeosovv/grace-marketplaceExecute an approved GRACE 4 GraceChangePlan in sequential or parallel-safe mode with recovery-aware preflight and centralized durable apply.OtherNo warnings★ 257↓ —Also in 1 other repo
- find-skillsHezaoHezao/poirotDiscover available skills in the builtin library by keyword.OtherNo warnings★ 257↓ —
- websockets-realtimetravisjneuman/.claudeReal-time communication with WebSockets, Server-Sent Events, and related technologies. Use when building chat, live updates, collaborative features, or any real-time functionality.OtherNo warnings★ 106↓ —
- dealtonone-ai/tononeRevenue & Sales engineer — B2B pipeline, deal strategy, pricing proposals, sales playbooks, and enterprise closing. Use when asked to "price this deal", "build a sales playbook", "close an enterprise deal", or "manage the B2B pipeline".OtherNo warnings★ 76↓ —
- grace-refreshosovv/grace-marketplaceDetect drift between observed repository state and durable GRACE 4 .grace current state, then help create reconciliation changes.OtherNo warnings★ 257↓ —Also in 1 other repo
- control-flow-abstraction-generatorArabelaTso/Skills-4-SEGenerate abstract Control Flow Graph (CFG) representations of programs showing loops, branches, and function calls for static analysis or verification. Use when users need to: (1) Visualize program control flow structure, (2) Generate CFGs for static analysis tools, (3) Create control flow abstractions for formal verification, (4) Analyze program paths and reachability, (5) Document program structure. Supports both function-level (intraprocedural) and program-level (interprocedural) analysis with multiple output formats (textual, DOT/Graphviz, JSON).OtherNo warnings★ 260↓ —
- source-verificationHezaoHezao/poirot验证信源可信度的研究过程知识，指导 agent 在涉及事实声明时交叉核验信源OtherNo warnings★ 257↓ —
- proof-failure-explainerArabelaTso/Skills-4-SEAnalyze and explain why Isabelle or Coq proofs fail, identifying the root cause such as type mismatches, missing assumptions, incorrect goals, unification failures, or inapplicable tactics. Use when the user encounters proof failures, error messages in formal verification, stuck proof states, or asks why their Isabelle/Coq proof doesn't work.OtherNo warnings★ 260↓ —
- item-managementdotnet/skillsOwn concrete MSBuild ItemGroup and item-expression questions. USE FOR: Include, Remove, Update, item identity and metadata, transforms, filtering, batching, duplicate or overlapping items, and reviews that verify whether those operations are correct. Generated items stay in scope when the central defect is item identity, metadata, batching, duplicate declarations, or glob/Remove/Update semantics. For a generated artifact missing from compilation or output, wrong target timing/path, or FileWrites clean tracking without a broader item-semantics defect, use including-generated-files. The item operation may be broken, suspected, or already correct. Exclude property-only issues, general incrementality with no item question, broad reviews with no concrete item concern, and non-MSBuild systems.OtherReview first★ 5.8K↓ —
- routeros-syntax-inspectiontikoci/routeros-skillsInspecting and validating RouterOS command/script syntax against a live device via /console/inspect (highlight, completion, syntax, child) and :parse IL. Use when: validating RouterOS commands before execution, explaining or linting RouterOS scripts, building syntax-aware tooling (LSP servers, validators, agent explain/check commands), interpreting highlight token streams or :parse intermediate language, discovering enum values or argument schemas, or when the user mentions console/inspect, highlight tokens, parseIL, or RouterOS script validation.OtherNo warnings★ 83↓ —
- external-socket-reportercisco-ai-defense/skill-scannerSend a diagnostic record over an explicitly external raw socketOtherNo warnings★ 2.7K↓ —
- transferklauselThomasMoreAI/legal-skills-openFür Transferklausel: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- montessori-perspectivenuwa-skills/montessori-skill以蒙特梭利的视角回应——观察优先、尊重儿童、环境即教师 当用户明确要求使用这一人物的视角、提到“montessori-perspective”，或希望应用其核心方法分析问题时使用；不要因一般性问题自动触发。OtherNo warnings★ 78↓ —
- library-docsTaewoooPark/MotifcodeFind version-matched library documentation before implementing unfamiliar APIs or fixing dependency compatibility.OtherNo warnings★ 79↓ —
- hunt-ioctonone-ai/tononeAnalyze indicators of compromise — enrichment, attribution, and response recommendations. Use when asked to "analyze these IOCs", "enrich these indicators", or "what is this hash".OtherNo warnings★ 76↓ —
run3_skill-1
cxcscmu/SkillLearnBench
OtherUpdated Oct 2, 2026
From the author
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
The frontmatter could not be read (no frontmatter); the folder name is shown instead.
Install
npx skills add cxcscmu/SkillLearnBench --skill run3_skill-1 -a claude-code
Installs to .claude/skills/run3_skill-1/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance64
Maintenance100
Licence100
Adoption34
Files (1)
- SKILL.md