Analyze images and generate comprehensive JSON profiles for style recreation. Use when users upload images for visual analysis, style extraction, AI image generation prompts, or need detailed breakdowns of composition, lighting, color, and subject elements.
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
Template for creating new Claude Code skills following official specification. Provides structure, YAML frontmatter format, and best practices for skill development.
Use when implementing on-device AI with Apple's Foundation Models framework — prevents context overflow, blocking UI, wrong model use cases, and manual JSON parsing when @Generable should be used. iOS 26+, macOS 26+, iPadOS 26+, visionOS 26+
Universal agent configuration patterns for any AI coding environment. Use when configuring steering, specs, or context assembly for Kiro, Claude Code, Codex, Charm, or other agents.
Expert knowledge for Application Layer modeling in Documentation Robotics
MCP (Model Context Protocol) Server development guide. Use when building Claude Code extensions. Covers Tools, Resources, Prompts capabilities.
This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.
コンテキストサイズを監視し、作業中に自動 compact が走らないよう事前にコンテキストを圧縮する。「コンテキストを圧縮して」「compact して」「メモリを整理」「会話を整理」「履歴を圧縮」「コンテキストが大きい」「動作が重い」などで起動。操作がない時やタスクの区切りでコンテキストが一定ラインを超えていたら自動的に /compact を実行。
Use this skill when the user wants to create a new project, set up a new repository, or scaffold a new codebase. This includes when they say things like "create a new project", "set up a new app", or "initialize a new repository".
无头模式 AI CLI 调用技能：支持 Gemini/Claude/Codex CLI 的无交互批量调用，包含 YOLO 模式和安全模式。用于批量翻译、代码审查、多模型编排等场景。
Build RAG systems - embeddings, vector stores, chunking, and retrieval optimization
Implement mitigations, create input filters, design output guards, and build defensive prompting for LLM security
AI agent applies a 5-phase systematic framework for tackling complex problems when conventional approaches fail. Use when stuck, blocked, or troubleshooting issues.
Search through past session context and observations. Use when asking about past work, previous implementations, how something was done before, or recalling decisions. Keywords: remember, recall, last time, before, history, what did we, how did we
Build AI applications on Azure using Azure OpenAI, Cognitive Services, and ML services with enterprise patterns
LLM invocation patterns from hooks via SDK. Use when you need background agents, CLI calls, or cost optimization.
Prompt caching for Claude API to reduce latency by up to 85% and costs by up to 90%. Activate for cache_control, ephemeral caching, cache breakpoints, and performance optimization.
IMPORTANT: Activate this skill BEFORE modifying any skill in ~/.claude/skills/. Guide for creating, updating, and maintaining Claude Code skills following best practices. Use proactively when: (1) creating a new skill, (2) modifying an existing skill in ~/.claude/skills/, (3) user requests to create, improve, update, review, or refactor a skill, (4) discussing skill quality or effectiveness. Always commit skill changes to the skills git repository after making modifications.
Guide for creating 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).
Recursive Language Model context management for processing documents exceeding context window limits. Enables Claude to match Gemini's 2M token context capability through chunking, sub-LLM delegation, and synthesis.
