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.
47,289 skills from 2,272 repositories · updated 26 seconds ago
10,066 skills
- hunt-uploadEncod3d-Sec/TORCHFile upload attack hunting - extension/content-type/magic-byte bypass to web-shell RCE, path traversal in filename, SVG/XML XSS, zip slip, and pixel-flood DoS. Wiki-first, FIND schema output.OtherNo warnings★ 336↓ —
- redteamleadEncod3d-Sec/TORCHOn-demand senior red-team lead advisor. Call at a decision point or obstacle to get wiki-grounded direction instead of hammering blindly. Dispatches a fresh RTL subagent that reads the engagement state + evidence + wiki and returns ranked directions with an explicit STOP. Use for "redteamlead", "RTL", "I'm stuck", "where do I go", "what next", "which vector", "should I keep hammering this".OtherNo warnings★ 336↓ —
- next-moveEncod3d-Sec/TORCHRanked next offensive moves from engagement state. Reads state/loot/Killchain, runs the deterministic analyzer, elaborates the top move. Use when asked "what next", "where to focus", "prioritize", or at the start of an engagement session.OtherNo warnings★ 336↓ —
- negotiationThomasMoreAI/legal-skills-openFür Negotiation Strategy Battlecards: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Großkanzlei Corporate/M&A. Route: negotiation.OtherNo warnings★ 95↓ —
- zhuangxiu-fengge-dapei-zhinanzx029w/zhuangxiu-skills装修风格选择与搭配指南专用 Skill。覆盖风格怎么选、主流风格（北欧/现代简约/新中式/日式/法式/美式/奶油/原木/侘寂/轻奢/中古/欧式等）怎么装不踩坑、风格配色与软装搭配、风格与预算省钱做法，倒序整合西安装修课堂20年精华知识库，帮用户选对风格、装出想要的效果。OtherNo warnings★ 86↓ —
- realtime-collaboration-expertroedyrustam/vibes-plugReal-time collaboration: WebSockets, WebRTC, and CRDTs (Yjs) / Kolaborasi real-time: WebSockets, WebRTC, dan CRDT (Yjs).OtherNo warnings★ 115↓ —
- latchkeyimbue-ai/latchkeyInteract with third-party or self-hosted services (Slack, Google Workspace, Dropbox, GitHub, Linear, Coolify...) using their HTTP APIs on the user's behalf.OtherNo warnings★ 132↓ —
- hunt-cacheEncod3d-Sec/TORCHWeb cache poisoning + cache deception hunting - unkeyed input poisoning, cache-key analysis, path-confusion deception, header/parameter cloaking. Wiki-first, FIND schema output.OtherNo warnings★ 336↓ —
- monte-carlo-asset-healthmonte-carlo-data/mc-agent-toolkitCheck the health of a data table/asset using Monte Carlo. Activates on "how is table X", "check health of X", "is X healthy", "status of X", "check on X table", or any health/status question about a data asset.OtherNo warnings★ 93↓ —
- leasing-agbThomasMoreAI/legal-skills-openFür Leasing AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- incident-managementBagelHole/DevOps-Security-Agent-SkillsImplement incident management processes and escalation procedures. Configure on-call schedules and post-incident reviews. Use when managing production incidents.OtherNo warnings★ 1.2K↓ —
- wechat-coauthorYiShu5/claude-skills协助意疏写「意疏的AI口袋」公众号文章。Claude 是协作者不是写手——voice 必须从意疏嘴里出来，AI 负责结构化、扩写、降 AI 味。触发：写公众号文章 / 帮我整理口述 / 有素材但想不清 / 这段 AI 味太重 / 看看有没有意疏味道 / 帮我把骨架写成文章。输出 Markdown，排版找 wechat-formatter，发布找 wechat-publisher。OtherNo warnings★ 131↓ —
- public-maThomasMoreAI/legal-skills-openFür Public M&A, Kapitalmarkt und MAR: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Großkanzlei Corporate/M&A.OtherNo warnings★ 95↓ —
- d3-data-tablecxcscmu/SkillLearnBenchBuild interactive HTML data tables with D3.js v6, including row highlighting and click-based selection synced with charts.OtherNo warnings★ 91↓ —
- b2b-shop-b2cThomasMoreAI/legal-skills-openFür B2B-Shop und Unternehmernachweis: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- bildrechte-kiThomasMoreAI/legal-skills-openKlärt Bildrechte, Karten, Tabellen und Drittmaterial für Print, E-Book, Plattform und Werbung; baut eine belegte Rechtekette mit Schutzgegenstand, Rechteinhaber, Nutzungsart, Gebiet, Dauer, Quellenangabe und Freigabestatus.OtherNo warnings★ 95↓ —
- lizenz-patent-patgThomasMoreAI/legal-skills-openFür Lizenz Patent (PatG): ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- apple-intelligencershankras/claude-code-apple-skillsApple Intelligence skills for on-device AI features including Foundation Models, Visual Intelligence, App Intents, and intelligent assistants. Use when implementing AI-powered features.OtherNo warnings★ 837↓ —
- bonus-rabattThomasMoreAI/legal-skills-openFür Bonus Rabatt: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- screenshot0xDarkMatter/claude-modsFind and display recent screenshots. Triggers: screenshot, check screenshot, show screenshot, recent screenshot, last screenshot.OtherNo warnings★ 78↓ —
- frontier-ai-models-expertroedyrustam/vibes-plugFrontier AI models orchestration (Grok 4.7, Gemini 4, Claude 5.5) / Orkestrasi model AI frontier (Grok 4.7, Gemini 4, Claude 5.5).OtherNo warnings★ 115↓ —
- js-backend-expertroedyrustam/vibes-plugExpert-level skill for Node.js 24+ (LTS), Bun 1.2+, and Deno 2.x backend development. Covers Express 5, Fastify 5, Hono v4, NestJS, Prisma 6, Drizzle ORM, WebSockets, BullMQ, OpenTelemetry, and microservices in English and Indonesian.OtherNo warnings★ 115↓ —
- find-replace0xDarkMatter/claude-modsModern find-and-replace using sd (simpler than sed) and batch replacement patterns. Triggers on: sd, find replace, batch replace, sed replacement, string replacement, rename.OtherNo warnings★ 78↓ —
- runbook-creationBagelHole/DevOps-Security-Agent-SkillsCreate operational runbooks and standard operating procedures. Document troubleshooting guides and recovery procedures. Use when documenting operational knowledge.OtherNo warnings★ 1.2K↓ —
simpo-loss
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 (invalid YAML: YAMLParseError: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Implements the S); the folder name is shown instead.
Install
npx skills add cxcscmu/SkillLearnBench --skill simpo-loss -a claude-code
Installs to .claude/skills/simpo-loss/ · 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