One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
oaustegardSkilloaustegard/claude-skills/creating-mcp-servers/SKILL.md
Creates production-ready MCP servers using FastMCP v2. Use when building MCP servers, optimizing tool descriptions for context efficiency, implementing progressive disclosure for multiple capabilities, or packaging servers for distribution.
justrachSkilljustrach/kuri/.claude/skills/kuri-server/SKILL.md
Use kuri-server to automate Chrome via HTTP API — navigate pages, get a11y snapshots, interact with elements, capture network traffic (HAR), extract cookies, and bypass bot protection. Use when the user wants to browse websites, scrape data, fill forms, test web apps, or interact with protected sites via a headless browser. Trigger phrases include "browse to", "open the page", "get the page content", "fill the form", "capture network traffic", "get cookies", "bypass bot protection".
patonkikhSkillpatonkikh/APES/skills/mcp/mcp-server-generator/skill.md
Generate a Model Context Protocol (MCP) server structure: transport layer, capability declarations, project layout, and bootstrap configuration for a new MCP integration. Use when working on scaffolding MCP servers, MCP transport setup.
Hack23SkillHack23/European-Parliament-MCP-Server/.github/skills/mcp-server-development/SKILL.md
MCP protocol patterns, tool implementation, resource handlers, prompt templates, and error handling for Model Context Protocol servers
kekzlSkillkekzl/imp/.claude/skills/server-api/SKILL.md
Use when working on or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).
llama-farmSkillllama-farm/llamafarm/.claude/skills/server-skills/SKILL.md
Server-specific best practices for FastAPI, Celery, and Pydantic. Extends python-skills with framework-specific patterns.
jamesdebattySkilljamesdebatty/skills/skills/mcp-server-patterns/SKILL.md
Design, implement, or review Model Context Protocol servers in Node.js or TypeScript, including tools, resources, prompts, schemas, transports, authorization, and operational safety. Use for MCP SDK work or protocol integration decisions.
pankaj-mahaurSkillpankaj-mahaur/Agent-Daemon/skills/mcp-server-patterns/SKILL.md
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
tabgabSkilltabgab/opp_repl-skill/opp-repl-mcp-server/SKILL.md
Connect an AI agent to opp_repl via its built-in Model Context Protocol (MCP) server. Two transports — a Unix domain socket reached through the `opp_repl_mcp_bridge` stdio bridge (recommended for local tools like Claude Code, Cursor, VS Code, Windsurf) and a TCP/streamable-HTTP port with bearer-token auth (for remote/legacy clients). Exposes the `execute_python` tool plus opp-repl:// documentation resources. Load when wiring opp_repl into an MCP-capable client.
ddalcuSkillddalcu/mlx-serve/skills/mlx-serve/SKILL.md
Hook an app, game or script up to the local mlx-serve server for LLM chat, embeddings, image, speech, music, video and 3D generation, and Laya typed decisions. Use when code should call mlx-serve.
vellum-aiSkillvellum-ai/vellum-assistant/skills/mcp-setup/SKILL.md
Add, authenticate, list, and remove MCP (Model Context Protocol) servers — connect any external tool or service that publishes an MCP endpoint to the assistant
PracticalSwanSkillPracticalSwan/agent-skills/netlify-mcp-servers/SKILL.md
Build, deploy, and secure Model Context Protocol (MCP) servers on Netlify. Use whenever the task involves creating an MCP server, exposing an app or API to AI agents as MCP tools, letting Claude / Cursor / Claude Code call a custom remote server, or adding MCP tools to an existing Netlify site. Covers the MCP SDK + Streamable HTTP transport on a Netlify Function, authentication (single shared secret vs per-user API keys with Netlify Identity), read/write safety, file uploads, and connecting clients. Use even when the user just says \"MCP\", \"tool server for an agent\", or \"let an AI use my API\".
VercelSkillvercel-labs/json-render/skills/mcp/SKILL.md
MCP Apps integration for json-render. Use when building MCP servers that render interactive UIs in Claude, ChatGPT, Cursor, or VS Code, or when integrating json-render with the Model Context Protocol.
briandconnellySkillbriandconnelly/skills/bundle-uv-mcp-server/SKILL.md
Use when packaging, validating, or distributing a uv-managed Python MCP server (new or existing) as an MCPB bundle (.mcpb) for Claude Desktop or another MCPB host. Triggers include creating an MCPB manifest.json, setting server.type to uv, bundling a uv + pyproject.toml stdio server, running mcpb pack or mcpb validate, preparing one-click install, and exposing API tokens or install-time settings through user_config. Scoped to the MCPB packaging step (manifest_version 0.4+); not for authoring the server's tools or handlers, designing/reviewing/auditing MCP tool/resource/prompt schemas, Node servers, or cloud-only remote HTTP servers.
GitHubSkillgithub/awesome-copilot/skills/mcp-security-audit/SKILL.md
Audit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: - Reviewing .mcp.json files for security risks - Checking MCP server args for hardcoded secrets or shell injection patterns - Validating that MCP servers use pinned versions (not @latest) - Detecting unpinned dependencies in MCP server configurations - Auditing which MCP servers a project registers and whether they're on an approved list - Checking for environment variable usage vs. hardcoded credentials in MCP configs - Any request like "is my MCP config secure?", "audit my MCP servers", or "check .mcp.json" keywords: [mcp, security, audit, secrets, shell-injection, supply-chain, governance]
bloknayrbSkillbloknayrb/tandem/.claude/skills/dev-server/SKILL.md
Start Tandem dev environment (server + client) and verify MCP connection
smixsSkillsmixs/disruptor-skills/skills/setup-server/SKILL.md
A prompt template for safely provisioning a production Ubuntu/Debian web server (Docker Compose, reverse proxy, TLS, firewall, SSH hardening) without lockouts or data loss.
ProxiBlueSkillProxiBlue/claude-skills/server-scan/SKILL.md
Comprehensive Magento 2 server security investigation and compromise detection. Use when investigating a potentially compromised server, scanning for malware, detecting webshells, or performing post-incident forensics.
mjunaidcaSkillmjunaidca/mjs-agent-skills/.claude/skills/building-mcp-servers/SKILL.md
Guides creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). Covers tool design, authentication, Docker deployment, and evaluation creation. NOT when consuming existing MCP servers (use the server directly).
GitHubSkillgithub/awesome-copilot/skills/typescript-mcp-server-generator/SKILL.md
Generate a complete MCP server project in TypeScript using the MCP TypeScript SDK v2 (@modelcontextprotocol/server) with tools, resources, and proper configuration
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
