Agent skills

Skills matching “agent”

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
1,221 found
145192 · page 4 / 26
open-agent-teamsDelegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal…AI-Builder-Clubsubagents-orchestration-guideGuides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases…shinpr00-build-your-claude-agent-skillCreate your Claude Agent SDK skill in one prompt, then learn to improve it throughout the chaptermajiayu000003-agents-installationUse when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination…majiayu000200-agents-mdUse when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure…majiayu0002026-legal-research-agentExpert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns…majiayu00034-openai-agents-sdkCreate your OpenAI Agents SDK skill in one prompt, then learn to improve it throughout the chaptermajiayu00035-google-adk-reliable-agentsCreate your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chaptermajiayu00039-agent-skills-mcp-code-executionCreate a skill that orchestrates the write-execute-analyze loop to autonomously process data. Learn to implement error recovery…majiayu00039-agent-skills-mcp-code-execution-panaversity-agentfactoryBuild a specification-first Digital FTE that orchestrates accumulated intelligence from Lessons 1-7. Learn to compose execution…majiayu000agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…majiayu00042-openai-apps-sdk-panaversity-agentfactoryCreate your OpenAI Apps SDK skill in one prompt, then learn to improve it throughout the chaptermajiayu00071-agent-framework-integrationCreate your agent-integration skill from OpenAI SDK and LiteLLM documentation before learning framework integrationmajiayu00080-livekit-agents-majiayu000-claude-skill-registrCreate your LiveKit Agents skill from official documentation, then learn to improve it throughout the chaptermajiayu000add-agent-templatesAdd new Agent templates to the meta-agent-skills framework.majiayu000adk-agent-builderBuild production-ready AI agents using Google's Agent Development Kit with AI assistant integration, React patterns, multi-agent…majiayu000writesadk-rag-agentBuild RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A…majiayu000advanced-agentdb-vector-search-implementationMaster advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid…majiayu000agent-ai-engineerExpert AI engineer specializing in AI system design, model implementation, and production deployment. Masters multiple AI…majiayu000agent-api-designerAPI architecture expert designing scalable, developer-friendly interfaces. Creates REST and GraphQL APIs with comprehensive…majiayu000agent-api-documenterExpert API documenter specializing in creating comprehensive, developer-friendly API documentation. Masters OpenAPI/Swagger…majiayu000agent-architecture-plannerUse when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Claude Code…majiayu000agent-assistantAgent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger…majiayu000writesagent-auditWhen reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft.…majiayu000agent-auditValidates agent configurations for model selection, tool permissions, focus areas, and approach quality. Use when reviewing…majiayu000writesagent-authoringGuide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus…majiayu000writesagent-boosterWASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.a5c-aiwritesagent-bricksCreate and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and…majiayu000agent-bricksCreate and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and…majiayu000agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…majiayu000agent-browserBrowser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots…majiayu000agent-browserBrowser automation via agent-browser CLI for web navigation, form filling, screenshots, scraping, login flows, and UI testing.BioTender-maxagent-browserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to…majiayu000Agent BrowserA fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and…majiayu000agent-browserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to…majiayu000agent-browserブラウザを手足のように操る。ページ遷移、フォーム入力、スクショ、なんでもこい。Use when users ask to navigate websites, fill forms, take screenshots, extract web data…majiayu000writesagent-browserHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selectionmajiayu000agent-browserBrowser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots…majiayu000agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…majiayu000agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…majiayu000agent-browserBrowse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data…majiayu000agent-browserBrowser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots…majiayu000agent-browserAgent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating…majiayu000agent-builderCreates Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, and system prompts. Use when…majiayu000agent-builderBuild custom AI agents in Claude Code from a user's problem statement. This skill analyzes the user's use case, asks smart…majiayu000agent-builderUse when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool…majiayu000Agent CreatingUsed to create a new agent. Used when a user wants to create a new agentmajiayu000agent-builderDesign and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI…majiayu000
← Prev4 / 26Next →
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