Community生產力與協作github.com

mcp-use/mcp-builder

**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP development or mcp-use patterns - Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets This skill contains critical architecture decisions, security patterns, and common pitfalls. Always consult the relevant reference files BEFORE implementing MCP features.

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/mcp-use/mcp-use/tree/main/skills/mcp-builder

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

說明文件

mcp-use/mcp-builder

MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP development or mcp-use patterns - Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets This skill contains critical architecture decisions, security patterns, and common pitfalls. Always consult the relevant reference files BEFORE implementing MCP features.

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

相關技能

randomittin/heimdall

Autonomous Claude Code agent — 14 specialized agents, 10-parallel execution, project-specific skill learning, mechanical checkpointing, wave-based planning with acceptance gates, caveman ultra (~75% token savings). One prompt → finished project.

community

launchdarkly/launchdarkly-flag-create

Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Use when the user wants to create a new flag, wrap code in a flag, add a feature toggle, or set up an experiment. Guides exploration of existing patterns before creating.

community

hdeng416/wechat-claude-code

Chat with Claude Code from WeChat - a Claude Code Skill

community

dzianissokalau/autonomous-roadmap-delivery

Codex-native, file-backed workflow for delivering phased roadmaps one phase at a time with verification, review gates, durable state, and safe automation controls.

community

api-evangelist/anthropic

Anthropic is an AI safety company and creator of the Claude family of large language models. The Anthropic API provides access to Claude models for text generation, vision, tool use, extended thinking, batch processing, and agentic workflows. Anthropic also publishes the Model Context Protocol (MCP) for standardized AI tool integration.

community

openai/openai-docs

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.

community