撰寫高品質、符合現代最佳實踐的 CSS 程式碼。專為 netiCRM/CiviCRM 專案優化，強制要求選擇器加上 .crm-container 前綴以隔離樣式。解決 AI 常見問題：避免暴力解法(如濫用 !important)、使用現代 CSS 特性取代舊方法、建立可維護的架構、正確理解 Box Model 和 Stacking Context。當需要撰寫、修改、檢查、審查、分析、評估...
4-layer knowledge capture system for development sessions. Use when user says /mem (quick capture), /distill (extract patterns), /td (post-task retrospective with Before/After context), /improve...
Fetch up-to-date documentation for any library using the Context7 API. Use when the user needs accurate, current docs for a framework, library, or SDK (e.g., React, Next.js, Langchain). Two-step...
Creates, updates, or optimizes CLAUDE.md files following Anthropic best practices. Use when user requests creating, updating, improving, or optimizing CLAUDE.md files for project context, coding...
Validate technical feasibility with minimum code before full implementation. Prove ONE atomic question ('Can I X?') through 6-phase workflow: SCOPE, CONTEXT, MINIMUM, EXECUTE, VERIFY, CAPTURE. Use...
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on...
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on...
Comprehensive HPK (proprietary healthcare message format) parser and explainer. Supports 100+ message types across patient administration (ID, MV, CV), supply chain (PR, FO, MA, CO, LI, RO, FA),...
Use when needing to scrape documentation websites into markdown for AI context. Triggers on "scrape docs", "download documentation", "get docs for [library]", or creating local copies of online...
Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help...
Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use when asked to "optimize docs", "improve agent knowledge", "make docs more...
Comprehensive concurrency and parallelism patterns for multi-threaded and async programming. Use when implementing async/await, parallel processing, thread safety, worker pools, or debugging race...
Use when content must be translated between audiences with different expertise, context, or goals while preserving accuracy but adapting presentation. Invoke when technical content needs business...
Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context...
Creates educational Teams channel posts for internal knowledge sharing about Claude Code features, tools, and best practices. Applies when writing posts, announcements, or documentation to teach...
Synthesize information across multiple sources into a structured document. Processes sources in batches across sessions to handle more data than fits in context. Discovers and queues related...
Create technical diagrams using Mermaid syntax for architecture, sequences, ERDs, flowcharts, and state machines. Use for visualizing system design, data flows, and processes. Triggers: diagram,...
Guide for creating high-quality Model Context Protocol (MCP) servers. Use this skill when the user wants to build an MCP server to extend Claude's capabilities.
Fast workflow for small changes, bug fixes, and UI tweaks that don't require full feature development. Uses sub-agent orchestration with model selection (Sonnet 4.5 orchestrator, Haiku 4.5...
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis...