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
memory-rag-instrumentation
仪器 RAG 检索、内存操作和上下文管理
tool-call-tracking
对工具执行进行带有适当上下文和错误处理的仪表化
llm-call-tracing
Instrument LLM API calls with proper spans, tokens, and latency
multi-agent-coordination
Instrument multi-agent workflows, handoffs, and parent-child relationships
state-flow-visualizer
分析和可视化 LangGraph 管道中的状态流。在调试状态突变、跟踪节点之间的数据流、识别孤立状态键、检测读/写依赖性或生成状态转换的美人鱼图时使用。触发诸如“可视化状态流”、“跟踪状态键”、“哪些节点接触 X”、“状态依赖性”、“调试状态突变”、“孤立状态键”、“状态流程图”等短语。
mood
跟踪清晰度、成长、参与度、连接和能量方面的内部状态。用于理解和传达当前能力。
visualizing-subagents
在启动代理前,使用ASCII图可视化子代理任务依赖,完成后创建全面的HTML总结。
transcript-condenser
Condenses Claude Code session transcripts into readable summaries by filtering metadata, system notifications, and command artifacts. Use when the user wants to review, analyze, or understand what happened in a Claude Code session, view tool usage patterns, or export session data. Triggers when user mentions "analyze session", "review transcript", "condense logs", "what tools did I use", or similar workflow analysis requests.
claude-mobile-cost-tracking
Use when implementing Claude API cost tracking, monitoring token usage, displaying cost metrics in Settings, or user asks about costs - calculates exact costs using $0.003/1k input and $0.015/1k output pricing with per-session aggregation
agent-debugging
Debug and troubleshoot ElevenLabs conversational AI agents and Twilio calls. Use when diagnosing agent issues, analyzing failed calls, troubleshooting audio problems, investigating conversation breakdowns, reviewing error logs, or optimizing underperforming agents. Includes transcript analysis, error diagnosis, and performance troubleshooting.
recovering-sessions
恢复崩溃、失败或中断的Claude Code会话。在以下情况下使用此技能:会话在多代理并行执行时崩溃、需要确定已完成与未完成的工作、想要生成中断任务的恢复命令、从上下文窗口耗尽中恢复或处理会话移交。分析代理日志、验证磁盘状态,并创建带有可执行Task()命令的恢复计划。
tzurot-observability
Use when adding logging, debugging production issues, checking service health, or performing routine operations (adding personalities, database queries). Covers structured logging, correlation IDs, Railway log analysis, and common operations.
introspect
灵魂自我反省(Svadhyaya)。用于诊断性能、寻找改进或检查智慧健康。
streaming-output
实时流格式化程序的输出格式标记。在构建流分析提示时使用,以确保正确的进度显示。记录 StreamFormatter 检测和显示的模式。
session-analyzer
Discovers and lists Claude Code session transcripts from .claude/logs/ for analysis. Use when the user wants to find available sessions, view session timelines, identify which sessions to analyze for workflow improvements, or understand session history. Triggers when user mentions "what sessions do I have", "analyze my workflow", "show my recent sessions", "find transcripts from [date]", or similar session discovery requests.
agents
List all AI agents with versions and deployment status. Use when checking agent health, versions, or deployment state.
longitudinal-drift-detector
Detect behavioral drift and alignment degradation over time.
claude-get-session-info
共享获取Claude PID和会话ID的脚本。在其他脚本中引用此脚本以访问CLAUDE_PID和SESSION_ID变量。
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。