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.
47,966 skills from 2,309 repositories · updated 19 hours ago
10,103 skills
- glm-basicscxcscmu/SkillLearnBenchSet up and validate the GLM environment for Lake Mendota simulation. Use this skill to verify the configuration file exists, inspect current calibration parameters, and confirm all input data (meteorological forcing, field observations, initial profile) are accessible before running calibration.OtherNo warnings★ 91↓ —
- anfaenger-modusThomasMoreAI/legal-skills-openFür Kaltstart und Orientierung: Erklärt begriffe wie freiberuf: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- word-stil-tonThomasMoreAI/legal-skills-openFür Word: Erstprüfung, Rollenklärung und Mandatsziel: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- ressort-bmiThomasMoreAI/legal-skills-openFür Ressort-Heranführung BMI: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- audit-agent-surfaceJoviDeCroock/prachtInventory what agents can reach in a pracht app — capability exposure (HTTP, WebMCP, remote MCP), `agents` trust config, the destructive-confirmation gate, `llms.txt`, Markdown negotiation, OpenAPI — and report where the surface is wider than intended, or confirm an opt-out app ships none. Use for "audit the agent surface", "what can agents do on my site", "is my MCP endpoint safe", "did this PR widen what agents can reach".OtherNo warnings★ 105↓ —
- 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↓ —
- visualizationrobium-ai/robiumChoose between RViz2, Foxglove, Lichtblick, and Rerun to inspect robot behavior.OtherNo warnings★ 103↓ —
- 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↓ —
- matter-closeoutThomasMoreAI/legal-skills-openFür Matter Closeout: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- 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↓ —
- bmad-betaalvin-reyes/better-agentic-ideA wired skill with no record. Use when a golden needs an unregistered skill.OtherNo warnings★ 85↓ —
- oil-visualoil-oil/oil-visual制作统一漫画墨线风格的解释图与透明插画素材,可单独绘制眼镜线条人物、暖黄色牧羊犬、两者组合,或同风格的物件与装饰元素。当用户需要概念、机制、流程、对比的完整解释画面,或可复用的排版插图时使用;不用于普通代码图表、照片处理或无关品牌视觉。OtherNo warnings★ 105↓ —
- d3-bubble-chartcxcscmu/SkillLearnBenchHow to build a D3.js v6 force-directed bubble chart with sector clustering, size encoding, color legends, tooltips, and interactive selection. Use this skill whenever the user wants a bubble chart, force simulation, cluster layout, or interactive SVG circles with D3.OtherNo warnings★ 91↓ —
- deckungsklageThomasMoreAI/legal-skills-openFür Deckungsklage: erstellt Entwurf mit Antrag, Beweis und Anlagen; Ergebnis: Schriftsatz mit Begründungs- und Anlagenlogik. Fachgebiet: Fachanwalt Versicherungsrecht. Route: deckungsklage.OtherNo warnings★ 97↓ —
- ressort-aaThomasMoreAI/legal-skills-openFür Ressort-Heranführung AA: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- zeitnarrativeThomasMoreAI/legal-skills-openFür Zeitnarrative und Timesheet: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- intake-2ThomasMoreAI/legal-skills-openFür Intake und Eingangstriage: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- self-improveeai-org/agent-toolkitCapture durable user feedback into the governing skill, doc or check, or propose creating a new skill when no suitable one exists, so future sessions don't repeat the mistake. Use when the user rejects, reverts, or overrides the agent's output or approach on something a skill, doc or check covers or should cover, and when manually invoked to improve or create guidance.OtherNo warnings★ 79↓ —
- agentify-projecteai-org/agent-toolkitMake a project agent-ready by converging it toward a canonical agent-neutral structure. Re-runnable, and doubles as an audit.OtherNo warnings★ 79↓ —
- 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↓ —
- agent-ready-scan-sitefabricioctelles/skillsSub-skill: Scan any URL for agent readiness. Checks 23 standards across 5 categories, returns readiness level (0-5), status of all checks, and fix instructions.OtherNo warnings★ 123↓ —
- simpo-losscxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.OtherNo warnings★ 91↓ —
- create-readmeGulajavaMinistudio/awesome-copilot-idCreate a README.md file for the projectOtherNo warnings★ 91↓ —
- pet-friendly-filteringcxcscmu/SkillLearnBenchFiltering accommodations for pet-friendly stays by analyzing house_rules field in accommodation data.OtherNo warnings★ 91↓ —