Guides creation and editing of SKILL.md files following Anthropic best practices and this repo's conventions. Use when creating a new skill, editing an existing skill, porting a skill from another...

LLM application architecture expert for RAG, prompting, agents, and production AI systemsUse when "rag system, prompt engineering, llm application, ai agent, structured output, chain of thought,...

选题系统主控Agent。协调热点采集、选题生成、选题审核三个环节，支持迭代直到产出合格选题。触发方式：(1)"开始今日选题"启动完整流程 (2)"今日AI热点"只采集热点不生成选题 (3)"我有一个选题"进入单个选题分析 (4)"推荐一些好的选题"直接输出推荐。输出保存到Obsidian选题库。

Manages context passing between DAG nodes and spawned agents. Handles context summarization, selective forwarding, and token budget optimization. Activate on 'bridge context', 'pass context',...

This skill provides a complete SEO content workflow for creating, analyzing, and optimizing long-form blog content. Use when the user wants to research topics, write SEO-optimized articles,...

This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural...

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG,...

Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware...

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions...

|

This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive...

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context...

This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation,...

>

Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.

Analyzing user intent and delegating tasks.

作業記憶を永続化する。調査結果、設計判断、進捗などをマークダウンで保存し、セッション間で再利用可能にする。「記憶して」「思い出して」「記憶一覧」で発動。

|

Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation like file headers, function docs,...