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
performance-optimization
Use when animation runs slow, janky, or causes frame drops
troubleshooting-bundler-compatibility
Diagnose and fix third-party library loading failures in Vite, Webpack, or other bundlers. Use when encountering "Failed to fetch dynamically imported module", worker loading failures, CDN 404 errors, "Invalid type" errors when importing library assets, or assets loading in wrong format. Covers version mismatches, worker loading patterns, and bundler-specific solutions.
performance-expert
Expert performance optimization including profiling, bottleneck analysis, caching, and load testing
debugger
Expert debugging including error analysis, root cause identification, and systematic problem solving
debugging
Systematic debugging for Rust applications. Root cause analysis, loggingstrategies, profiling, and issue reproduction. All debug changes removedbefore final report.
swiftuice-analyze
This skill should be used when the user asks to find and fix SwiftUI performance issues, optimize SwiftUI views, fix re-render problems, or analyze why their iOS/macOS app UI is slow. It handles the full workflow from code review to trace analysis.
verify-debug-mode
通过AERA调试模式(调试视图、控制台、日志)确认请求的功能更改。当需要通过调试UI进行验证或需要添加仅调试的探针/命令以使更改可观察时使用。
backend-hang-debug
Diagnose and fix FastAPI hangs caused by blocking ThreadPoolExecutor shutdown in the news stream route; includes py-spy capture and non-blocking executor pattern.
storage-debug-instrumentation
Add comprehensive debugging and observability tooling for backend storage layers (PostgreSQL, ChromaDB) and startup metrics. Includes storage drift detection, raw data inspection endpoints, and a Next.js admin dashboard.
eds-performance-debugging
Adobe Edge Delivery Services的EDS块调试和性能优化指南,包括错误处理、FOUC预防、核心Web指标优化和调试工作流程。
full-stack-debugger
当调试跨越UI、后端和数据库层的全栈问题时应使用此技能。它提供系统化工作流程来检测错误、分析根本原因、迭代应用修复,并通过自动服务器重启和基于浏览器的测试验证解决方案。适用于调度器失败、导入错误、数据库问题或API负载问题等场景,这些问题起源于后端代码但表现在UI中。
debugger
当根本原因不明确时使用。通过调用栈追溯故障并隔离第一个错误状态。
debugging-with-tools
用于调查密集型工作。在更改代码前,首选工具驱动的证据(搜索、日志、差异)。
mobile-debugging
用于React Native/Expo故障排除(Metro bundler、原生模块、模拟器/模拟器问题)。
systematic-debugging
用于错误/测试失败。重现、隔离根本原因、修复并用证据验证。
code-debug-skill
Standardized, hypothesis-driven debug investigation workflow for unexpected behavior, regressions, incidents, flaky tests, or production issues. Use to plan instrumentation, reproduce with decisive signals, compare runs, and narrow root cause without assuming any vendor or infrastructure.
provider-config-validator
验证和调试Vercel AI SDK提供程序配置,包括API密钥、环境设置、模型兼容性和速率限制。在遇到提供程序错误、身份验证失败、API密钥问题、缺少环境变量、模型兼容性问题、速率限制错误或用户提及提供程序设置、配置调试或SDK连接问题时使用。
hypothesis-debugging
Structured code debugging through hypothesis formation and falsification planning. Use when diagnosing bugs, unexpected behaviour, or system failures where the root cause is unclear. Produces a hypothesis document for execution by another agent rather than performing the investigation directly. Triggers on requests to debug issues, diagnose problems, investigate failures, or create debugging plans.
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。