发现 devops llm ai 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。
Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, inte...
Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Automatically suggests updates to: DISCOVERIES.md (l...
Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.
6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration and understanding, not implementation. Includes parallel agent deployment for effi...
Creates, refines, and validates Claude Code skills following amplihack philosophy and official best practices. Automatically activates when building, creating, generating, or designing new skills.
6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration and understanding, not implementation. Includes parallel agent deployment for effi...
Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.
Performs quick research using web search and synthesis when user asks about unfamiliar topics, new technologies, or needs current information. Activates on questions like 'how does X work', 'what is Y', or when...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
Operate agentpack safely in Claude Code. Use /ap-* commands for execution; prefer --json.
Example Codex skill from Agentpack minimal repo template.
Gather and clarify requirements before autonomous pipeline execution. Interactive phase for user input.
Start the multi-AI pipeline with TDD-driven ralph loop. Plan → Review → Implement (loop until tests pass + reviews approve).
Implement code using sonnet model with full main context access
Reference guide for Claude Code skills system (January 2026). Use when creating, modifying, or understanding skills, SKILL.md format, frontmatter fields, hooks, context fork, or skill best practices.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT,...
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product...
Reference guide for Claude Code plugins system (January 2026). Use when creating, distributing, or understanding plugins, plugin.json schema, marketplace configuration, bundling skills/commands/agents/hooks/MCP...
Reference guide for Claude Code slash commands (January 2026). Use when creating custom commands, understanding command frontmatter, argument syntax, context fork, hooks, or plugin command namespacing.
This skill should be used when describing patterns or anti-patterns for detection by LLM agents across any domain (code analysis, business processes, security audits, UX design, data quality, medical diagnosis,...
When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI tools. When troubleshooting l...
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or desig...
Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md configurations, or Skill files. Transforms negative instructions into positive patte...
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When cod...
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。