发现 工具与集成 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Comprehensive guide for building production-ready agents with the Claude Agent SDK. Use when creating agents, designing tools, implementing subagents, managing sessions, integrating MCP servers, or understandin...
Common reasoning protocol shared across all subagents.
Orchestrate gummy-agents across distributed network using 'd' command for load-balanced, multi-host AI development
Autonomous skill extraction from debugging discoveries. Activates when agents find non-obvious solutions through investigation, experimentation, or trial-and-error. Captures these discoveries as reusable skills...
Imported skill init_skill from anthropic
Imported skill skill from openai
Extended investigation for technology evaluation, competitive analysis, architectural exploration, and best practices research. Unlike spike (time-boxed hours), deep-research supports multi-day comprehensive in...
Imported skill commands from langchain
Imported skill node_mcp_server from anthropic
Imported skill skill from anthropic
Extract reusable, non-obvious learnings from a completed task into new Codex agent skills (SKILL.md). Use when the user asks to run codeception, do a retrospective, save/extract a skill, or turn a workaround in...
Imported skill skill from langchain
Imported skill skills from langchain
Imported skill readme from langchain
Imported skill readme from anthropic
Imported skill init_skill from langchain
Manage the SoNash expansion evaluation process for reviewing ~280 feature and technical ideas across 21 modules. This skill should be used when the user wants to evaluate expansion ideas, track progress, make d...
Imported skill init_skill from openai
Imported skill claude from vercel
Create and maintain effective AGENTS.md files following OpenAI best practices. Keep instructions brief, unlock agentic loops, document gotchas, and reference task-specific files. Use when setting up or improvin...
Analyzes completed agent sessions to identify what went well, what went wrong, and patterns to improve. Reads from .claude/ folder (session logs, progress.md, git history) and produces actionable insights. Use...
Time-boxed technical investigation with structured output. Use for feasibility studies, architecture exploration, integration assessment, performance analysis, or risk evaluation. Creates spike tasks in ohno, e...
Strategies for effective time management, prioritization, and sustainable productivity for software developers
Ensure Acceptance Criteria map to Tasks and Tests for PR-per-story workflow
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。