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 effective collaboration with the strategist agent—a remote expert providing unbiased advice on complex architectural decisions, trade-offs, and problems where you're stuck or need outside perspective. Th...
Use this skill when Claude needs an outside perspective on complex problems, is stuck on a technical challenge, needs validation of an approach, or wants consultation on architectural decisions. Provides access...
Use this skill whenever important information is learned during a task or when the user explicitly asks to store something. Use when users ask to remember. Triggers on "remember this", "update memory", "share"...
创建有效技能的指南。当用户想要创建新技能（或更新现有技能）以通过专业知识、工作流程或工具集成来扩展 Claude 能力时，应使用此技能。
Track task steps and write reports to preserve context across agent sessions and avoid forgetting user intentions.
Build Retrieval Augmented Generation (RAG) systems for AI applications. Use when creating document Q&A systems, knowledge bases, semantic search, or any application combining retrieval with LLM generation. Trig...
Build AI agents with OpenAI's API. Use when creating tool-calling agents, multi-step reasoning systems, function calling implementations, or autonomous AI workflows. Triggers include "OpenAI agent", "function c...
Comprehensive FastAPI development skill for building Python web APIs from hello world to production-ready applications. Use when building REST APIs, implementing authentication, integrating databases, adding We...
Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.
Modern Python development with Python 3.12+, Django, FastAPI, async patterns, and production best practices. Use for Python projects, APIs, data processing, or automation scripts.
Coordinate multiple AI agents working in parallel using git worktree. Use when setting up parallel development across multiple worktrees or coordinating agent work.
Writes webnovel chapters (3000-5000 words) using v5.0 dual-agent architecture. Context Agent gathers context, writer produces pure text (no XML tags), review agents report issues, polish fixes problems, Data Ag...
Meta-skill that enables skills to evolve and improve themselves through performance monitoring, variant generation, and data-driven optimization. Use this skill when you need to create new self-evolving skills,...
Self-review before completing tasks. Multi-perspective verification using Gemini CLI + Claude subagent.
最简单的 Claude Code Skill 示例 - 向用户问好并展示基本结构
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...
Launch an autonomous coding loop that implements features through small, incremental user stories. Use when implementing new features that can be broken into small stories, working on tasks that benefit from it...
Deep module investigation using Amp's Search for discovery, oracle for expert analysis, and mermaid for visualization. Use when you need to understand complex code, prepare for refactoring, or debug issues.
Comprehensive computational mathematics toolkit for Claude Code agents. Provides tools for five core domains from MIT's Mathematics for Computer Science curriculum - Proofs (propositions, predicates, induction,...
State checkpointing, divergence detection, and confidence tracking for Hopper/Hardin doctrine compliance. Use PROACTIVELY when performing multi-step reasoning, external actions, or any task requiring error reco...
Shell prompt to Claude Code statusLine mirroring. Parses Bash PS1, Zsh PROMPT, Fish fish_prompt, and PowerShell prompt functions to generate compatible statusLine configuration. Use when users want their termin...
Conversational brainstorming that refines ideas through targeted questions, triggers codebase exploration, and prepares context for planning
明示的に呼び出されたときにのみ読み込みます。エージェントが自律的に呼び出す必要はありません。
明示的に呼び出されたときにのみ読み込みます。エージェントが自律的に呼び出す必要はありません。
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。