Work with the Unsloth MCP Server codebase. Use when maintaining, extending, or debugging this specific MCP server implementation. Provides architecture knowledge, code patterns, and development workflows.
Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.
Guide for using MSBuild Server to improve CLI build performance. Activate when developers report slow incremental builds from the command line, or when CLI builds are noticeably slower than IDE builds. Covers MSBUILDUSESERVER=1 environment variable for persistent server-based caching. Do not activate for IDE-based builds (Visual Studio already uses a long-lived process).
Make live IndyKite authorization decisions (AuthZEN/KBAC) and run ContX IQ graph queries from an AI agent over the Model Context Protocol - self-contained Bearer-token JSON-RPC calls on the stateless protocol (revision 2026-07-28), no session handshake and no bespoke REST wiring. Use when calling the IndyKite MCP server (server/discover, tools/list, authzen_evaluate, authzen_evaluations, authzen_search_*, ciq_execute), configuring an MCP server, or debugging its single Bearer-token auth.
Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth posture.
Browse, search, and recommend geospatial / GIS / mapping / earth-observation MCP servers, and add newly discovered ones to the tracked list. Use when the user asks "is there an MCP server for <geospatial thing>", wants to find a geocoding/routing/PostGIS/STAC/imagery/weather MCP server, or says they found a new geo MCP server to track.
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
Start the local webpack dev server and connect to it with the Playwright browser. Use this skill when asked to start the dev server, preview the app, or interact with the running application in a browser.
Model Context Protocol (MCP) server implementation specialist for Claude Desktop integration. Handles TypeScript/Node.js server scaffolding, endpoint creation, telemetry setup, npx distribution, and comprehensive documentation. Follows MCP specification and best practices for production-grade server deployment.
Design a SaaS product's MCP server as a product surface AI agents operate - sizing the build investment, curating a 5-15 workflow-tool agent surface instead of mirroring API endpoints, named write-tool safety patterns (scoped credentials, read-only lockdown, human-in-the-loop approval, risk-tiered server-side gates, dry-run preflight, idempotency and spend caps), remote hosting with OAuth 2.1, versioning the tool surface, MCP registry discoverability, and measuring agent adoption. Use whenever the user mentions MCP, Model Context Protocol, an agent-facing tool surface, exposing a product to AI agents or coding assistants, or MCP write-tool safety - even if they never say "MCP server". Design layer only - code-generation MCP builder skills scaffold what this specifies.
Build production-ready Model Context Protocol (MCP) servers using the official MCP SDK. Scaffold, configure, secure, and deploy MCP servers with best practices for security, monitoring, and reliability. Use for creating robust MCP servers that integrate with Claude Code.
Use when building, installing or registering a personal MCP server — adding its `[project.scripts]` entry point, installing it with `uv tool install` from a local checkout or straight from git instead of publishing to PyPI, registering it with `claude mcp add` and choosing local/project/user scope, switching between an editable dev install and a released one without re-registering, and the per-repo dev loop (`inv dev-env.setup`, `inv quality.precommit`, why automation needs `uv run inv`) for the repos that produce these servers.
ALWAYS LOAD THIS SKILL when working with FileServer, SMB, SMB2, SMB3, CIFS, file sharing, MS-SMB2, MS-FSCC, MS-FSA, MS-DFSC, MS-FSRVP, MS-RSVD, MS-SQOS, or any file server protocol test implementation. This skill assists with writing FileServer protocol test cases, implementing new test scenarios, discovering reusable libraries, adapters, and transport implementations (TCP, QUIC, NetBIOS, RDMA). CRITICAL--Before implementing any test, first classify the domain by analyzing concepts (File*, Fs*, FileSystemAttributes = FSA; NEGOTIATE, SESSION_SETUP, SMB commands = SMB2). Test scenarios from MS-SMB2 that involve File*/Fs* concepts belong to the FSA test suite. Provides test case patterns, storage locations, ProtoSDK usage, and test execution guidance. Protocols under FileServer/src include Auth, Common, DFSC, FSA, FSAModel, FSRVP, RSVD, ServerFailover, SMB2, SMB2Model, and SQOS.
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.
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.
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.
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 or AGENTS.md?
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.
What is a skill?
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.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.