Claude Skills 中文技能市场——为 Claude Code、Codex 与 Cursor 精选 Agent Skills
收录 90,000+ 开源 SKILL.md 工作流,提供中文解读、安全检测与高速下载,一行命令即可装到你的 AI 编程助手里。
高分中文技能
root-cause-tracing
系统性地向后跟踪调用栈中的bug以找到原始触发器
debugging
四阶段调试框架,确保在修复前识别根本原因。在遇到错误、测试失败、意外行为或先前修复尝试失败时使用。强制执行先调查纪律("调试这个"、"修复这个错误"、"测试失败"、"不工作")。
debugging
フロントエンドとバックエンドのデバッグを支援します。エラーの原因特定、ログの確認、型エラーの修正、実行時エラーの解析、Tauri 通信のデバッグなどに使用します。
coderabbit-fix
Implement fixes for specific CodeRabbit review issues. Runs in isolated subagent context with focused task. Verifies fixes with tests before returning. Use one per issue from triage task list.
debugging
Systematic debugging strategies and techniques
root-cause-analysis
Root cause analysis frameworks for debugging
debugger-detective
⚡ PRIMARY TOOL for: 'why is X broken', 'find bug source', 'root cause analysis', 'trace error', 'debug issue', 'find where X fails'. Uses claudemem v0.3.0 AST with context command for call chain analysis. GREP/FIND/GLOB ARE FORBIDDEN.
mobile-perf
Optimizes React Native Expo applications for speed, responsiveness, and battery efficiency. Use when fixing lag, optimizing lists, or reducing bundle size.
debug-detective
适用于任何代码库、任何语言、任何错误类型的系统化调试方法
performance-hunter
在任何语言或框架中查找并修复性能瓶颈
session-replay
Set up session replay for visual debugging. Use when implementing DOM recording with privacy controls.
source-map-setup
Configure source maps for readable stack traces. Use when setting up error tracking, debugging production issues, or configuring build tools.
detecting-incorrect-free
Detects incorrect use of free() including freeing non-heap memory, invalid pointers, and mismatched allocators. Use when analyzing memory deallocation, heap management, or investigating free() usage errors.
detecting-memory-leaks
Detects memory leak vulnerabilities by identifying unfreed memory allocations and missing cleanup in error paths. Use when analyzing long-running processes, resource management, or investigating memory exhaustion issues.
root-cause-tracing
Systematically trace bugs backward through call stack to find original trigger
error-handling
API响应、React错误边界、webhook处理、面向用户的消息和Baselime监控的全面错误处理模式。
divi-5-compatibility
Use this skill when validating CSS for Divi 5 compatibility, checking for unsupported features, troubleshooting Divi CSS issues, or when the user mentions CSS not working in Divi. Provides compatibility rules, validation patterns, and fixes for common issues.
arcanea-systematic-debug
系统调试方法——基于假设测试、隔离和根本原因分析的科学研究方法来查找和修复错误。基于Arcanean原则,理解先于执行。
常见问题
什么是 Claude Skills(Agent Skills)?
Skills 是一种标准化的 SKILL.md 指令包——把「何时触发、如何执行、使用哪些工具」写成结构化工作流,装入 Claude Code、Codex、Cursor 等 AI 编程助手后,Agent 遇到对应任务会自动调用,效果远好于每次手写提示词。
装了 Skill 之后怎么使用?
安装后无需手动调用:直接在 Claude Code / Cursor 里描述你的任务(如「帮我做 PR 代码审查」),Agent 检测到匹配的技能后会自动加载对应 SKILL.md 并按其流程执行。也可以在对话中显式要求「使用 xx skill」。
国内如何高速下载安装?
本站在 Cloudflare R2 托管了全部技能 ZIP 离线包,无需直连 GitHub:在详情页点击「Download ZIP」,或用 `npx skills add <owner/repo>` 一键安装;也可以复制 curl 命令直接解压到 ~/.claude/skills 目录。