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 11 hours ago
9,541 skills
- resp-recontonone-ai/tononeAudit existing incident response capability — playbook coverage, tooling gaps, and readiness. Use when asked to "audit our incident response", "assess IR readiness", or "find playbook coverage gaps".OtherNo warnings★ 76↓ —
- numerical-integrationparcadei/Continuous-Claude-v3Problem-solving strategies for numerical integration in numerical methodsOtherNo warnings★ 3.9K↓ —
- background-agent-pingsparcadei/Continuous-Claude-v3Background Agent PingsOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- loogle-searchparcadei/Continuous-Claude-v3Search Mathlib for lemmas by type signature patternOtherNo warnings★ 3.9K↓ —
- propositional-logicparcadei/Continuous-Claude-v3Problem-solving strategies for propositional logic in mathematical logicOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- bonus-rabattThomasMoreAI/legal-skills-openFür Bonus Rabatt: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- integration-theoryparcadei/Continuous-Claude-v3Problem-solving strategies for integration theory in measure theoryOtherNo warnings★ 3.9K↓ —
- fabric-patternaAAaqwq/AGI-Super-TeamIntegrate Daniel Miessler's Fabric patterns into local workflows for structured prompting, text transformation, and retrieval-assisted processing.OtherNo warnings★ 112↓ —
- verjaehrungThomasMoreAI/legal-skills-openFür Verjährung von Handelsvertreter-Ansprüchen nach Paragraf 195 ff. BGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- natural-transformationsparcadei/Continuous-Claude-v3Problem-solving strategies for natural transformations in category theoryOtherNo warnings★ 3.9K↓ —
- konzernrechtThomasMoreAI/legal-skills-openFür Konzernrecht: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- echo-jobstonone-ai/tononeJobs-to-Be-Done analysis — given a product, user descriptions, transcripts, or tickets, produce a JTBD job map with switching forces analysis and opportunity ranking. Use when asked to "find the JTBD", "what jobs are users hiring us for", "job mapping", "what are users really trying to do", "JTBD framework", or "why are users switching".OtherNo warnings★ 76↓ —
- serv-recontonone-ai/tononeAudit existing serverless functions — find misconfigurations, cold start issues, and cost inefficiencies. Use when asked to "audit our serverless functions", "find function misconfigurations", or "check serverless cost issues".OtherNo warnings★ 76↓ —
- warden-iamtonone-ai/tononeBuild IAM from scratch — roles, policies, service accounts with least privilege. Use when asked to "set up IAM", "create roles", "service accounts", or "access control".OtherNo warnings★ 76↓ —
- mint-runwaytonone-ai/tononeCalculate and extend runway — current cash, burn rate, runway months, and the levers available to extend it. Use when asked to "how long is our runway", "when do we run out of money", or "what cuts extend runway by 6 months".OtherNo warnings★ 76↓ —
- predicate-logicparcadei/Continuous-Claude-v3Problem-solving strategies for predicate logic in mathematical logicOtherNo warnings★ 3.9K↓ —
- categories-functorsparcadei/Continuous-Claude-v3Problem-solving strategies for categories functors in category theoryOtherNo warnings★ 3.9K↓ —
- content-classificationcxcscmu/SkillLearnBenchClassify documents by subject using keyword matching and text analysisOtherNo warnings★ 91↓ —
- de-ai-ifyaAAaqwq/AGI-Super-Team将AI生成的机械化文本转换为自然、有人情味的人类写作风格OtherNo warnings★ 112↓ —
- chatbot-messaging-expertroedyrustam/vibes-plugExpert guide for chatbot and messaging platform integration (WhatsApp Business, Telegram Bot, Discord.js, Slack Bolt) and conversational AI / Panduan ahli integrasi chatbot dan platform messaging (WhatsApp Business, Telegram Bot, Discord.js, Slack Bolt) dan AI percakapan.OtherNo warnings★ 115↓ —
- banach-spacesparcadei/Continuous-Claude-v3Problem-solving strategies for banach spaces in functional analysisOtherNo warnings★ 3.9K↓ —
- hilbert-spacesparcadei/Continuous-Claude-v3Problem-solving strategies for hilbert spaces in functional analysisOtherNo warnings★ 3.9K↓ —
- prime-numbersparcadei/Continuous-Claude-v3Problem-solving strategies for prime numbers in graph number theoryOtherNo warnings★ 3.9K↓ —
- library-docsTaewoooPark/MotifcodeFind version-matched library documentation before implementing unfamiliar APIs or fixing dependency compatibility.OtherNo warnings★ 79↓ —
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 onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance64
Maintenance100
Licence100
Adoption34
Files (1)
- SKILL.md