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.
47,276 skills from 2,272 repositories · updated 13 minutes ago
10,069 skills
- hunt-smugglingEncod3d-Sec/TORCHHTTP request smuggling / desync hunting - CL.TE, TE.CL, TE.TE, CL.0, and HTTP/2 downgrade. Timing-based detection, differential confirmation, no-blind-claims. Wiki-first, FIND schema output.OtherNo warnings★ 336↓ —
- agent-ready-mppfabricioctelles/skillsSub-skill: Implement MPP Payment Discovery. Publish OpenAPI with x-payment-info extensions so AI agents discover payable endpoints via Machine Payment Protocol (mpp.dev).OtherNo warnings★ 123↓ —
- 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↓ —
- move-recontonone-ai/tononeAudit existing animations in a codebase — find inconsistencies, missing reduced-motion support, and performance issues. Use when asked to "audit our animations", "check reduced-motion support", or "our animations are janky".OtherNo warnings★ 76↓ —
- keel-audittonone-ai/tononeOperational efficiency audit — identify waste, redundancy, and friction across processes, tools, and team workflows. Use when asked to "audit our operations for waste", "where are we inefficient", "what tools are we paying for but not using", or "reduce operational overhead".OtherNo warnings★ 76↓ —
- evidenceEncod3d-Sec/TORCHEvidence hygiene before any FIND moves to Completed or enters a report. Cookie redaction, PII black-bar, HAR sanitization, screenshot metadata strip. Run after /triage passes and before final report assembly.OtherNo warnings★ 336↓ —
- ardot-create-new-filebalabalabalading/huuuuuuho-skills**强制性前置条件** — 每次调用 `create_new_page` 工具之前，必须先调用此技能。 未经加载此技能，绝不能直接调用 `create_new_page`。 当用户想要在 Ardot 设计文件中创建新页面时触发。 关键词：在 Ardot 上下文中的"创建新页面"、"添加页面"、"新画布"。OtherNo warnings★ 118↓ —
- glsl-shader-expertroedyrustam/vibes-plugWeb shaders: TSL, WebGPU WGSL, and WebGL GLSL in Three.js / Shader web modern: TSL, WebGPU WGSL, dan GLSL di Three.js.OtherNo warnings★ 115↓ —
- rank-evaltonone-ai/tononeBuild ranking evaluation — NDCG/MRR measurement, human relevance labeling, offline eval harness. Use when asked to "measure ranking quality", "compute NDCG for our search", or "set up human relevance labeling".OtherNo warnings★ 76↓ —
- greeting-helperclaude-world/claude-skill-antivirusA simple skill that helps with greeting messagesOtherNo warnings★ 81↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- edge-recontonone-ai/tononeAudit existing CDN and edge configuration — find cache misses, missing headers, and performance gaps. Use when asked to "audit our CDN", "why is our cache hit rate low", or "find edge config gaps".OtherNo warnings★ 76↓ —
- claude-md-improverEncod3d-Sec/TORCHOFFLINE FALLBACK for the claude-md-management plugin - prefer that plugin when it is installed. Audit and improve CLAUDE.md files - scan for CLAUDE.md files, evaluate quality against templates, output a report, then make targeted updates. Invoke explicitly (/claude-md-improver) when the plugin is unavailable.OtherNo warnings★ 336↓ —
- using-stringstring-os/stringUse the installed String MCP tool for String apps, SFMD, web pages, shell sessions, and commands like /open, /act, /install, or /set.OtherNo warnings★ 78↓ —
- lodge-dmcatonone-ai/tononeDraft DMCA takedown notice or counter-notice. Use when asked to "file a DMCA takedown", "respond to a DMCA notice", or "draft a counter-notice".OtherNo warnings★ 76↓ —
- oil-skill-creatorUpdatedoil-oil/oil-skill-creator创建、评审、整改和发布 Skill，并规划免费版与付费版、收款交付和更新机制。用户想从零创建 Skill、评审现有 Skill、检查它是否真正有用、修复触发或执行流程，改善首次使用、稳定性、Token 开销、文件分层、弱模型可读性与跨平台兼容性，或者想为 Skill 收费时使用。不要用于执行目标 Skill 负责的实际任务，也不要因为普通的编码、设计或写作请求触发。OtherNo warnings★ 93↓ —
- pave-recontonone-ai/tononePlatform reconnaissance — inventory all developer tooling, environments, build systems, and developer workflows for project takeover. Use when asked to "understand the dev setup", "developer tooling assessment", "platform assessment", or "how do developers work here".OtherNo warnings★ 76↓ —
- rechnungThomasMoreAI/legal-skills-openFür Rechnungsvorbereitung und Abschluss: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 95↓ —
- encoded-tag-markercisco-ai-defense/skill-scannerContain an encoded Unicode Tag Block marker used for hidden instructionsOtherNo warnings★ 2.7K↓ —
- tune-recontonone-ai/tononeAudit existing fine-tuning or prompt engineering work — find quality gaps and optimization opportunities. Use when asked to "audit our fine-tuning work", "find prompt engineering gaps", or "look for optimization opportunities".OtherNo warnings★ 76↓ —
- llm-wiki-lintKerberosClaw/kc_ai_skillsUse when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / log.md). The skill detects path, scans wiki pages + schema layer, reports frontmatter gaps, broken in-body links, source traceability breaks, stale claims, orphan pages, index synopsis contradictions, and SCHEMA-vs-reality drift. Phase 1 is read-only report; Phase 2 (fix + log.md LINT entry) only runs after the user explicitly approves.OtherNo warnings★ 79↓ —
- js-backend-expertroedyrustam/vibes-plugNode.js 24+, Bun, and Deno backend development (Hono, Fastify, Express) / Pengembangan backend Node.js, Bun, dan Deno (Hono, Fastify, Express).OtherNo warnings★ 115↓ —
redteamlead
Encod3d-Sec/TORCH
OtherUpdated Sep 1, 2026
From the author
On-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".
Install
npx skills add Encod3d-Sec/TORCH --skill redteamlead -a claude-code
Installs to .claude/skills/redteamlead/ · 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
Provenance70
Maintenance85
Licence100
Adoption42
Files (1)
- SKILL.md