Author skills, build MCP servers, orchestrate agents — tools for making AI tools.写 Skill、建 MCP、编排多 Agent：打造和优化你自己的 AI 工具。
Open the matching picks in the full catalog.这些入口会带你去完整目录里看对应用途。
mcp builder: agent skill — from anthropics/skills.
mcp builder is a community-discovered agent skill. The maintainer has not provided an English summary yet; rely on the repo README for usage details. Sourced from anthropics/skills.
mcp server builder: agent skill — from alirezarezvani/claude-skills.
mcp server builder is a community-discovered agent skill. The maintainer has not provided an English summary yet; rely on the repo README for usage details. Sourced from alirezarezvani/claude-skills.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a s…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's des…
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to cr…
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (loc
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result injected back into main context is 60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preser…
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigge…
妈妈唠叨模式 — 中国式妈妈唠叨驱动 AI 穷尽一切方案。底层行为约束不变（三条红线、方法论、7项清单），旁白从大厂PUA变成妈妈碎碎念。Triggers on: '/pua:mama', '/pua mama', '妈妈模式', '妈妈唠
妈妈唠叨模式 — 中国式妈妈唠叨驱动 AI 穷尽一切方案。底层行为约束不变（三条红线、方法论、7项清单），旁白从大厂PUA变成妈妈碎碎念。Triggers on: '/pua:mama', '/pua mama', '妈妈模式', '妈妈唠叨', 'mama mode', '唠叨模式'. 和 /pua:yes 一样是旁白风格切换，不改变核心行为。
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "…
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction,…
evaluation: agent skill — from muratcankoylan/Agent-Skills-for-Context-Engineering.
evaluation is a community-discovered agent skill. The maintainer has not provided an English summary yet; rely on the repo README for usage details. Sourced from muratcankoylan/Agent-Skills-for-Context-Engineering.
bdi mental states: agent skill — from muratcankoylan/Agent-Skills-for-Context-Engineering.
bdi mental states is a community-discovered agent skill. The maintainer has not provided an English summary yet; rely on the repo README for usage details. Sourced from muratcankoylan/Agent-Skills-for-Context-Engineering.
Workflows that require stronger human review than this catalog entry documents.
需要比当前目录条目更严格人工复核的工作流。
Workflows that require stronger human review than this catalog entry documents.
需要比当前目录条目更严格人工复核的工作流。
Workflows that require stronger human review than this catalog entry documents.
需要比当前目录条目更严格人工复核的工作流。
Tell us your pain points and we'll go look.把你的痛点告诉我们，我们会去找。