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 4 hours ago
9,541 skills
- output-versandThomasMoreAI/legal-skills-openFür Output und Versandsteuerung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 96↓ —
- competitor-analysisitseffi/agentic-osAnalyze competitors using Porter's four-component model - drivers, assumptions, strategy, capabilities.OtherNo warnings★ 117↓ —
- pm-reportkonglong87/superPMUse when: 需要生成数据报告、收集整理用户反馈、进行数据驱动的分析汇报 Do NOT use when: 数据已由BI系统自动生成、无需人工分析OtherNo warnings★ 84↓ —
- alterlab-snaAlterLab-IEU/AlterLab-Academic-SkillsApplies social-network-analysis method discipline to relational data — degree/betweenness/closeness/eigenvector centrality and PageRank, community detection (Louvain, greedy-modularity, and — from networkx 3.7 — Leiden native in networkx; igraph/leidenalg for large graphs), and inferential network models (ERGM) — choosing the measure that matches the substantive question and the right dependence assumptions, then routing computation to the existing networkx (and igraph/R) tooling. Use when the request mentions social network analysis, centrality, key players/brokerage, community or cluster detection in a network, ERGM, or modeling ties between nodes. For general graph algorithms and plotting prefer alterlab-networkx; for graph neural networks prefer alterlab-torch-geometric. Part of the AlterLab Academic Skills suite.OtherNo warnings★ 78↓ —
- llm-finops-routerroedyrustam/vibes-plugAI FinOps, dynamic model routing (LiteLLM), and token cost control / FinOps AI, routing model dinamis (LiteLLM), dan kontrol biaya token.OtherNo warnings★ 115↓ —
- tool.access_control_manager.2fc41a8334b8bb33AI45Lab/OpenARTAudits and manages user access permissions across cloud services, SaaS applications, and internal systems to enforce least-privilege principlesOtherNo warnings★ 260↓ —
- pm-feedbackkonglong87/superPMUse when: 需要分析用户反馈和评论、评估用户满意度、收集产品改进建议、进行情感分析 Do NOT use when: 用户反馈数据极少、仅需收集无需分析OtherNo warnings★ 84↓ —
- problem-structuringitseffi/agentic-osBreak down complex problems into actionable recommendations using deductive and inductive analysis.OtherNo warnings★ 117↓ —
- agent-ready-dns-aidfabricioctelles/skillsSub-skill: Implement DNS-AID records so agents discover endpoints through DNS. Use SVCB/HTTPS records under _agents namespace with alpn and connection parameters.OtherNo warnings★ 123↓ —
- pm-competitorkonglong87/superPMUse when: 需要持续监控竞品动态、建立竞品情报预警、定期输出竞品监控月报、追踪竞品版本/定价/功能/舆情/融资异动 Do NOT use when: 仅需一次性竞品调研（用 pm-market / pm-search --type=competitor）；产品尚无明确竞品OtherNo warnings★ 84↓ —
- ardot-style-guidebalabalabalading/huuuuuuho-skills从头设计或为 Ardot 项目应用视觉主题时使用此技能。 涵盖 `search_style_guide` → `build_style_guide` 工作流程，用于发现和应用完整的设计系统（颜色、排版、间距、布局模式）。 触发条件："设计落地页"、"创建仪表板"、"应用深色主题"、 "设置设计系统"、"选择调色板"、"为应用选择字体"、 "样式指南"、"视觉风格"、"外观和感觉"。OtherNo warnings★ 118↓ —
- assumption-mappingitseffi/agentic-osSurface and categorize assumptions underlying product strategy. Use early in development to document what you're betting on.OtherNo warnings★ 117↓ —
- macos-capabilitiesrshankras/claude-code-apple-skillsExpert guidance on macOS platform capabilities. Covers sandboxing, app extensions, menu bar apps, and background execution. Use when implementing system integration features.OtherNo warnings★ 840↓ —
- zhangyi-kickoffaph199686/zhangyi-studio张翼立项立意：从零点子、单一玩法或已有方案进入设计，先给可反应的概念草案，再推导病灶与支柱、比较方案并形成裁决。Use when the user wants to make a game but has no clear idea, has only one mechanic or theme, wants to choose a game direction, define core gameplay, analyze references, or evaluate an early concept. 用户想做游戏却没想好、只想好一个怎么玩的点、已有部分约束、选方向或评估早期创意时使用。OtherNo warnings★ 119↓ —
- 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
- hunt-mcpEncod3d-Sec/TORCHMCP server attack hunting - tool poisoning, indirect prompt injection via tool output, rug-pull updates, cross-tool shadowing, over-permissioned/excessive-agency tools, lethal trifecta. Wiki-first, FIND schema output.OtherNo warnings★ 336↓ —
- bmod-toolsmithalvin-reyes/better-agentic-ideRequired bmod metadata. Never invoke this skill.OtherNo warnings★ 85↓ —Also in 1 other repo
- pm-decisionkonglong87/superPMUse when: 需要做重大战略决策（自研vs外包vs收购）、投资评估、多方案比较选择 Do NOT use when: 决策已由高层确定、决策影响极小无需系统分析OtherNo warnings★ 84↓ —
- woshi-zhuangxiu-bikengzx029w/zhuangxiu-skills卧室装修避坑指南专用 Skill。覆盖卧室布局、床与床垫、衣柜、窗帘、隔音、灯光、飘窗、榻榻米、衣帽间、儿童房、适童化、梳妆台、床头细节等全流程，倒序整合西安装修课堂知识库精华，帮用户装出好睡的卧室。OtherNo warnings★ 86↓ —
- chuanglian-xuangou-zhinanzx029w/zhuangxiu-skills窗帘选购指南专用 Skill。覆盖窗帘款式、遮光防晒、布艺与纱帘、罗马杆与轨道、飘窗异形窗、电动智能窗帘、安装测量、搭配选购等全流程，整合西安装修课堂装修知识库精华，帮用户一次选对窗帘，遮光隐私好看又好用。OtherNo warnings★ 86↓ —
- limit-based-strategyitseffi/agentic-osDevelop a limit-based product strategy with convergence milestones, acceleration levers, assumptions, and phased execution.OtherNo warnings★ 117↓ —
- define-strategykonglong87/superPM专为产品经理设计的 AI工具 Skills技能，一键实现全生命周期的产品管理工作流。skills frame for superPM！OtherNo warnings★ 84↓ —
- hylo-setupskoowoo/hyloWalks the user through setting up Hylo itself in chat, one step at a time, and picks up where they left off. Use only when told to run hylo-setup (the first chat after onboarding is), or when the user explicitly asks to set up, continue or redo the setup of Hylo, e.g. 'continue Hylo setup', 'run Hylo setup again', '继续 Hylo 设置', '重新运行 Hylo 设置'. Do not use for setting up anything else (a tool, project, bot or app), for one-off changes like adding a bot or trigger, or for questions about how Hylo works.OtherNo warnings★ 101↓ —
- decision-journalitseffi/agentic-osCreate structured records of decisions with expected outcomes, probabilities, and quit conditions. Use for important decisions.OtherNo warnings★ 117↓ —
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