Guide for creating MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers, integrating external APIs, implementing tool servers, or creating agent capabilities. Covers TypeScript/Python patterns, tool design, and evaluation creation.
建立有效技能的指南。當使用者想要建立新技能（或更新現有技能）以透過專業知識、工作流程或工具整合來擴展 Claude 的能力時，應使用此技能。
Master AI agent fundamentals - architectures, ReAct patterns, cognitive loops, and autonomous system design
Template for creating Claude Code skills. Use this as a starting point when building new skills for code formatting, testing, documentation generation, or other specialized workflows. Include both functionality and usage triggers in descriptions.
DEPRECATED - Merged into work-command-center as Phase 0. Use work-command-center instead.
Use when creating new skills or editing existing skills - applies prompt engineering principles to write clear, goal-focused process documentation that trusts LLM intelligence
Use this skill for multi-step development tasks. Latent Chain Mode reduces token usage by 70-80% through hidden-state reasoning with 4-phase workflow: analysis → plan → impl → review.
Creates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Gathers context from codebase, conversation, and authentic sources before creating adaptable skills.
Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, prompts, and security best practices
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Create and configure Claude Code sub-agents with custom prompts, tools, and models
Persistent long-term agent memory for storing and querying past work, patterns, and learnings.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Expert knowledge for API Layer modeling in Documentation Robotics
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
Expert guidance for creating, configuring, and deploying Model Context Protocol (MCP) servers. Use when building custom MCP servers, integrating external APIs, or extending Claude with new capabilities.
Agent evaluation methods including LLM-as-judge, rubrics, and quality gates.
Security best practices for deploying AI/ML models to production environments
