Agent skills

AI & Agents skills

4,965 skills an agent can load when the work is AI & Agents — read straight from the source repositories, with what each one does, what ships alongside it, and where it came from.

Toolclaude-code 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
4,965 found
4,8494,896 · page 102 / 104
veo-automationAutomate Veo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQvercel-automationAutomate Vercel tasks via Rube MCP (Composio): manage deployments, domains, DNS, env vars, projects, and teams. Always search…davepoonvercel-automationAutomate Vercel tasks via Rube MCP (Composio): manage deployments, domains, DNS, env vars, projects, and teams. Always search…sickn33verificationUse when checking whether agent edits are reflected in the OpenChatCut project and editor.0xslineverification-loopA comprehensive verification system for OpenAI Codex sessions.mturacverifiedemail-automationAutomate Verifiedemail tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQveriphone-automationAutomate Veriphone tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQvero-automationAutomate Vero tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQqdrant-vertical-scalingGuides Qdrant vertical scaling decisions. Use when someone asks 'how to scale up a node', 'need more RAM', 'upgrade node size'…githubvestaboard-automationAutomate Vestaboard tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQvibe-agentsGenerate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, set up AI…KhazPwritesvibe-coding-architecture教非技术背景的人看懂技术架构、做好技术选型——把"只会照搬话术的小白"练成"能看穿方案好坏的人"。 当用户问"该用什么技术/框架"、"帮我选技术栈"、"AI 给的方案我看不懂"、"这几个方案怎么选", 或者需要把 demo 做成更正经的东西、要理解 AI…Junliu1066vibe-coding-harness质检 Agent:检查 vibe-coding-kit 其他 Skill 的产出物是否符合治理规范。 当用户说"检查一下产出"、"帮我看看合不合规"、"质检"、"验证 PRD"、"检查项目说明书", 或在任何 Skill 完成产出后,使用此 Skill…Junliu1066vibe-coding-prd一个"访谈式"的需求 Agent:通过一问一答 + 在岔路口给建议,把一个说不清需求的人,带到一份 AI 能直接照着开工的 PRD。 当用户说"我想做个 XX 但不知道怎么跟 AI 说"、"帮我理需求"、"帮我写个…Junliu1066vibe-coding-production把验证过的 Vibe Coding demo,做成能长期运行、给别人用的正式系统。 当用户说"想上线"、"怎么部署"、"这个 demo 想做成正式的"、"要注意安全吗"、"怎么测试我的项目", 或者准备把代码开源/公开发布时,使用此…Junliu1066vibe-coding-requirementsVibe Coding(用 AI 写代码)项目的第一步:把模糊的想法,变成 AI 能精准落地、不会跑偏的需求。 当用户说"我想做一个 XX"、"帮我用 AI 做个 demo"、"我有个想法想验证"、"帮我跟 AI 对齐需求",…Junliu1066vibe-coding-survivalVibe Coding(用 AI 写代码)开发过程中的避坑与自救——真正翻车大多发生在"开工后"。 当用户说"AI 越改越乱"、"demo 改坏了退不回去"、"AI 老忘记之前说的"、"功能越加越多很乱"、 "AI 说做好了但其实没用",或者正在用 AI…Junliu1066vibration-analysisExpert skill for modal analysis, frequency response, and vibration characterization of mechanical systemsa5c-aiwritesvirustotal-automationAutomate Virustotal tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQvisme-automationAutomate Visme tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQvmas-simulator-guideVectorized multi-agent reinforcement learning simulatorbrycewang-stanfordvqc-trainerVariational quantum classifier training skill with gradient optimizationa5c-aiwriteswaboxapp-automationAutomate Waboxapp tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwachete-automationAutomate Wachete tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwaiverfile-automationAutomate Waiverfile tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwakatime-automationAutomate Wakatime tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwandb-experiment-loggerExecute wandb experiment logger operations. Auto-activating skill for ML Training. Triggers on: wandb experiment logger, wandb…jeremylongshorewriteswannier90-tight-bindingWannier90 skill for maximally localized Wannier functions and tight-binding model constructiona5c-aiwriteswar-game-orchestratorBusiness war game orchestration skill for competitive response simulation and strategic testinga5c-aiwriteswarranty-claims-processorStreamlined warranty claim validation and processing skill improving customer satisfaction and reducing processing timea5c-aiwriteswasm-agentCreate and manage sandboxed WASM agents for isolated code executionruvnetwriteswaste-minimization-analyzerWaste minimization analysis skill for source reduction, recycling, and treatment optimizationa5c-aiwriteswastewater-optimizationSpecialized skill for biological and physical-chemical wastewater treatment process optimization with activated sludge modeling…a5c-aiwriteswater-distribution-modelerWater distribution system modeling skill for pipe networks, pump analysis, and fire flowa5c-aiwriteswati-automationAutomate Wati tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQWave Accounting AutomationWave Accounting toolkit is not currently available as a native integration. No Wave-specific tools were found in the Composio…ComposioHQwave_accounting-automationAutomate Wave Accounting tasks via Rube MCP (Composio): invoices, customers, payments, and small business accounting. Always…ComposioHQwave-planning-optimizerAutomated wave planning and pick path optimization skill to maximize warehouse throughput and order accuracya5c-aiwritesweathermap-automationAutomate Weathermap tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwebflow-automationAutomate Webflow CMS collections, site publishing, page management, asset uploads, and ecommerce orders via Rube MCP (Composio).…davepoonwebflow-automationAutomate Webflow CMS collections, site publishing, page management, asset uploads, and ecommerce orders via Rube MCP (Composio).…sickn33webscraping-ai-automationAutomate Webscraping AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwebshop-action-executorThis skill executes a specific interface action, such as clicking a button or selecting an option, within a web shopping…zjunlpwebvizio-automationAutomate Webvizio tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQwechat-official-account-llm-concept-explanationA reusable skill for authoring WeChat Official Account articles that explain core LLM concepts (e.g., quantization, continual…ECNU-ICALKwhatsapp-automationAutomate WhatsApp Business tasks via Rube MCP (Composio): send messages, manage templates, upload media, and handle contacts.…davepoonwhatsapp-automationAutomate WhatsApp Business tasks via Rube MCP (Composio): send messages, manage templates, upload media, and handle contacts.…sickn33whautomate-automationAutomate Whautomate tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQ
← Prev102 / 104Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going