Use when managing context window usage, compressing long sessions, or optimizing token usage. Triggers on keywords like "context", "memory", "tokens", "compress", "summarize session", "context limit", "optimize context".
Comprehensive LLM prompt engineering and optimization workflow that orchestrates expert analysis, advanced techniques, and multi-domain optimization using the integrated toolset. Handles everything from basic prompt improvement to complex multi-agent prompt orchestration.
Anthropic's official prompt engineering best practices. Use when optimizing prompts, debugging outputs, or improving response quality.
会话学习技能 - 分析当前会话，提取学习并持久化到三层存储（项目 CLAUDE.md、用户 CLAUDE.md、Memory MCP）
Modify Clawd, the Claude Code mascot. Use this skill when users want to customize Clawd's appearance in their Claude Code CLI, including changing colors (blue Clawd, green Clawd, holiday themes), adding features (arms, hats, accessories), or creating custom ASCII art variants. Triggers include "change Clawd color", "give Clawd arms", "customize the mascot", "modify Clawd", "make Clawd [color]", or any request to personalize the Claude Code terminal mascot.
LLMのパフォーマンス、信頼性、制御性を本番環境で最大化するための高度なプロンプトエンジニアリング技術をマスターします。プロンプトの最適化、LLM出力の改善、または本番環境プロンプトテンプレートの設計時に使用します。
Dual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL).
Analyzes user questions and automatically dispatches optimal agents/skills/plugins
Generate high-quality images from text prompts using fal.ai's text-to-image models. Supports intelligent model selection, style transfer, and professional-grade outputs.
Expert knowledge for building AI agents with Argentic - a Python microframework for async MQTT-based agents with multi-LLM support, custom tools, and multi-agent orchestration
Use Hugging Face Smolagents framework for code-based agentic research with tool support. Supports multiple LLM providers and web search.
Select appropriate Claude model (Opus 4.5, Sonnet, Haiku) for agents, commands, or Task tool invocations based on task complexity, reasoning depth, and cost/speed requirements.
Helps authors create new Clix agent skills by first researching the latest Clix SDK + docs via the Clix MCP Server, then generating a complete skill folder (SKILL.md, references, scripts, examples) aligned with the conventions in this repository. Use when the user asks to create/author a new Clix skill, extend the skills library, or when the user types `clix-skill-creator`.
Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts
Intelligently truncate text while preserving content integrity and semantic coherence. Suitable for long text preprocessing, ensuring text does not exceed specified length limits
エージェント、メモリ、ツール統合パターンを備えたLangChainフレームワークを使用してLLMアプリケーションを設計します。LangChainアプリケーションの構築、AIエージェントの実装、または複雑なLLMワークフローの作成時に使用します。
Orchestrate multiple AI models (GLM, MiniMax, etc.) as workers using Pi Coding Agent with Claude as coordinator.
Guidelines for optimizing Claude rulesets and instruction files (CLAUDE.md, settings.json) using context efficiency principles. Includes strategies for skill extraction, progressive disclosure, token savings calculation, and deduplication. Manually invoke when optimizing rulesets, reducing context size, extracting content to skills, or improving ruleset organization.
Compress verbose prompts & context before LLM processing. This skill should be used when input exceeds 1500 tokens, contains redundant phrasing, or includes unnecessary context. Reduces tokens by 40-60%.
