AI Agents & MCP Skills
995 ai agents & mcp agent skills for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh. find-skills leads with 2.7M installs a month.
#Type
- 1find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…Jul 2026
- 2mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.Jul 2026
- 3google-agents-cli-adk-codeThis skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use…Jul 2026
- 4google-agents-cli-workflowThis skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent",…Jul 2026
- 5google-agents-cli-evalThis skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval…Jul 2026
- 6google-agents-cli-scaffoldThis skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add…Jul 2026
- 7google-agents-cli-observabilityThis skill should be used when the user wants to "set up tracing", "monitor my ADK agent", "configure logging", "add observability", "debug production…Jul 2026
- 8google-agents-cli-publishThis skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini Enterprise", "publish to Gemini…Jul 2026
- 9agent-toolsRun AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation.Jul 2026
- 10developing-genkit-jsDevelop AI-powered applications using Genkit in Node.js/TypeScript.Jul 2026
- 11agents-sdkBuild AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks,…Jul 2026
- 12mcp-apps-builder**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns.Jul 2026
- 13mcp-builder**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns.Jul 2026
- 14chatgpt-app-builder**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns.Jul 2026
- 15claude-automation-recommenderAnalyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers).Jul 2026
- 16agentsBuild voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice…Jul 2026
- 17agentic-engineeringOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.Jul 2026
- 18autonomous-loopsPatterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.Jul 2026
- 19mcp-server-patternsBuild MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP.Jul 2026
- 20agent-developmentThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…Jul 2026
- 21hook-developmentThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks",…Jul 2026
- 22command-developmentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command…Jul 2026
- 23agent-platform-skill-registryInteract with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills.Jul 2026
- 24build-mcp-serverThis skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to…Jul 2026
- 25prompt-engineerWrites, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites.May 2026
- 26build-mcp-appThis skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build…Jul 2026
- 27build-mcpbThis skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP",…Jul 2026
- 28ai-agent-builderBuild AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patternsJan 2026
- 29gemini-agents-apiManages custom Agent resources on Gemini Enterprise Agent Platform.Jul 2026
- 30chatgpt-app-builderGuide developers through creating and updating ChatGPT apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects,…Jul 2026
- 31agent-platform-rag-engine-managementManage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK.Jul 2026
- 32agent-platform-prompt-managementManages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform.Jul 2026
- 33livekit-agentsBuild voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI",…Jun 2026
- 34agent-platform-model-registryAgent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the…Jul 2026
- 35mcp-developerUse when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources.May 2026
- 36mcpMCP Apps integration for json-render. Use when building MCP servers that render interactive UIs in Claude, ChatGPT, Cursor, or VS Code, or when integrating…Jul 2026
- 37apollo-mcp-serverGuide for using Apollo MCP Server to connect AI agents with GraphQL APIs.Jul 2026
- 38applyApply LaunchDarkly SDK onboarding: install dependency (or dual-SDK pair), configure env and secrets with consent, add init at entrypoint(s), verify compile.Jul 2026
- 39agentforce-generateBuild, modify, debug, and deploy agents with Agentforce Agent Script.Jul 2026
- 40speech-engineAdd real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine.Jul 2026
- 41langchain4j-mcp-server-patternsProvides LangChain4j patterns for implementing MCP (Model Context Protocol) servers, creating Java AI tools, exposing tool calling capabilities, and…Jun 2026
- 42toolsGive your agents capabilities through tools (function calling).Jul 2026
- 43agent-graphsCreate and manage agent graphs — directed graphs of configs connected by edges with handoff logic.Jul 2026
- 44built-in-metricsInstrument an existing codebase with LaunchDarkly config tracking.Jul 2026
- 45configs-createCreate and configure configs in LaunchDarkly. Helps you choose between agent vs completion mode, create the config, add variations with models and prompts, and…Jul 2026
- 46harness-creatorBuild, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates,…Jul 2026
- 47elevenlabs-agentsBuild conversational AI voice agents on the ElevenLabs platform.Jul 2026
- 48agent-memory-mcpA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).Jul 2026
- 49mcp-builderBuild MCP servers in Python with FastMCP. Define tools / resources / prompts, build the server, test locally, deploy to FastMCP Cloud or Docker.Jul 2026
- 50mcp2cliTurn any MCP server, OpenAPI spec, or GraphQL endpoint into a CLI.Jun 2026
- 51agent-analyze-code-qualityAgent skill for analyze-code-quality - invoke with $agent-analyze-code-qualityJul 2026
- 52agent-coderAgent skill for coder - invoke with $agent-coderJul 2026
- 53agent-adaptive-coordinatorAgent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinatorJul 2026
- 54verification-before-completion在宣称工作完成、已修复或测试通过之前使用，在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功；始终用证据支撑断言Jul 2026
- 55agent-tool-builderTools are how AI agents interact with the world. A well-designedJul 2026
- 56writing-plans当你有规格说明或需求用于多步骤任务时使用，在动手写代码之前Jul 2026
- 57skybridgeGuide developers through creating and updating ChatGPT and MCP apps.Jul 2026
- 58subagent-driven-development当在当前会话中执行包含独立任务的实现计划时使用Jul 2026
- 59using-git-worktrees当需要开始与当前工作区隔离的功能开发，或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在Jul 2026
- 60agent-orchestration-multi-agent-optimizeOptimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration.Jul 2026
- 61mcp-builderMCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力Jul 2026
- 62mcp-csharp-createCreate MCP servers using the C# SDK and .NET project templates.Jul 2026
- 63agents-best-practicesUse this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain.Jun 2026
- 64mcp-csharp-testTest C# MCP servers at multiple levels: unit tests for individual tools and integration tests using the MCP client SDK.Jul 2026
- 65answersUSE FOR AI-grounded answers via OpenAI-compatible /chat/completions.Jul 2026
- 66create-custom-agentCreates VS Code custom agent files (.agent.md) for specialized AI personas with tools, instructions, and handoffs.Jul 2026
- 67agents-connectUse when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies.Jul 2026
- 68agents-debugUse when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes.Jul 2026
- 69agents-optimizeUse when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization.Jul 2026
- 70agents-buildUse when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or…Jul 2026
- 71agents-get-startedUse when a developer wants to create a new agent project or get started with AgentCore.Jul 2026
- 72agents-hardenUse when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate…Jul 2026
- 73mcp-csharp-publishPublish and deploy C# MCP servers. Covers NuGet packaging for stdio servers, Docker containerization for HTTP servers, Azure Container Apps and App Service…Jul 2026
- 74ai-automation-workflowsBuild automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops.Jul 2026
- 75prompt-engineeringMaster prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts.Jul 2026
- 76mcp-configConfigure MCP (Model Context Protocol) servers for Claude Code. Manage MCP servers at user or project scope with best practices to avoid context pollution.Mar 2026
- 77alert-investigationInvestigates a triggered observability alert and returns a structured diagnosis with likely cause, scope, and next steps.Jul 2026
- 78microsoft-skill-creatorCreate agent skills for Microsoft technologies using official documentation.Jul 2026
- 79langgraph-architectureGuides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing…Jul 2026
- 80google-antigravity-sdkDesign, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK.Jul 2026
- 81ui-sound-designProgrammatic UI sound design using Web Audio API and Tone.js. Use when creating click sounds, notification chimes, toggle feedback, hover sounds, success/error…Apr 2026
- 82agent-architecture-analysisUse when auditing an agent codebase against the 12-Factor Agents methodology, reviewing LLM-powered system architecture, or assessing agentic app compliance.Jul 2026
- 83laravel-mcpLaravel MCP server development. Use when building MCP servers, tools, prompts, or resources for AI client integration.May 2026
- 84mcp-builderPlan and build MCP servers with agent-friendly tools, schemas, error handling, and evaluation. Use when creating or refactoring MCP integrations.Apr 2026
- 85skill-upperCreate, run, diagnose, and iteratively improve Agent Skill evaluations (evals) with the skill-up CLI / 使用 skill-up CLI 创建、运行、诊断并持续改进 Agent Skill 评测.Jul 2026
- 86agent-dx-cli-scaleA scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles.Jul 2026
- 87langgraph-implementationImplements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling…Jul 2026
- 88configure-canvas-mcpConfigure the Canvas Authoring MCP server for the current coauthoring session.Jul 2026
- 89deepagents-architectureGuides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing…Jul 2026
- 90skill-creatorCreate or update agent skills with concise SKILL.md instructions, bundled resources, agent metadata, validation, and packaging.Apr 2026
- 91inngest-agentsUse when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval,…Jul 2026
- 92bloomeryInteractive tutorial that guides engineers through building their own coding agent (agentic loop) from scratch using raw HTTP calls to an LLM API.Feb 2026
- 93prompt-injectionAudit applications for AI prompt injection, agent security, and LLM permission boundary vulnerabilities.May 2026
- 94mcp-app-builderGuide developers through creating and updating MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects,…Jul 2026
- 95add-mcscopilotAdds Microsoft Copilot Studio connector to a Power Apps code app.Jul 2026
- 96letta-configurationConfigure LLM models and providers for Letta agents and servers.Jul 2026
- 97deepagents-implementationImplements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting…Jul 2026
- 98generate-mcp-app-uiGenerate an MCP App widget (self-contained HTML) for an MCP tool. Describe the visual you want and paste your tool's test output.Jul 2026
- 99importing-chatgpt-memoryClone ChatGPT saved memory into Letta, then optionally enrich it with broader conversation history.Jul 2026
- 100agently-triggerflowUse when the user needs workflow orchestration such as branching, concurrency, approvals, waiting and resume, runtime stream, restart-safe execution, mixed…Jul 2026
