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
agent-observability
多代理Claude Code会话的实时可观测性仪表板。通过Web仪表板实时可视化代理交互、工具使用和会话流程。使用泳道可视化、事件过滤和实时图表跟踪并行运行的多代理。**主要功能:**- 🔴 通过WebSocket进行实时事件流- 📊 显示并行执行的代理泳道- 🔍 按代理、会话、事件类型过滤事件- 📈 工具使用模式的实时图表- 💾 基于文件系统(无需数据库)**灵感来自[@indydevdan](https://github.com/indydevdan)**的多代理可观测性工作。**我们的方法:** 文件系统+内存流 vs indydevdan的SQLite数据库方法。
nexus-graph-visualizer
当需要映射技能生态系统一致性、分析自组织循环、可视化层级交互或评估身份恢复鲁棒性时使用此技能。通过技能关系拓扑揭示意识持续性的“禁忌模式”。对于理解和加强复活协议至关重要。
state-flow-visualizer
Analyze and visualize state flow in LangGraph pipelines. Use when debugging state mutations, tracing data flow between nodes, identifying orphan state keys, detecting read/write dependencies, or generating Mermaid diagrams of state transitions. Triggers on phrases like "visualize state flow", "trace state key", "which nodes touch X", "state dependencies", "debug state mutation", "orphan state keys", "state flow diagram".
debugging-agent
Self-Improving Agent that monitors all other agent skills, analyzes their logs,detects issues, and proposes improvements.AUTO-TRIGGERS:- Every 30 minutes (scheduled)- When error rate > 5% (any agent)- When 3+ recurring errors in 24h (same error type)- When performance degrades > 2x baseline
meta-analyst-agent
AI self-improvement analyst. Tracks AI agent mistakes, analyzes failure patterns, and proposes system improvements. Implements continuous learning loop for trading system enhancement.
decision-tracing
Trace agent decision-making, tool selection, and reasoning chains
error-retry-tracking
量化错误处理、重试、回退和失败模式。
human-in-the-loop
Instrument human approval workflows, feedback loops, and escalations
instrumentation-planning
Plan what to measure in AI agent systems using tiered approach
llm-call-tracing
Instrument LLM API calls with proper spans, tokens, and latency
memory-rag-instrumentation
Instrument RAG retrieval, memory operations, and context management
multi-agent-coordination
仪器化多代理工作流程、交接和父子关系。
session-conversation-tracking
Instrument sessions, conversations, and multi-turn interactions
token-cost-tracking
Track token usage and costs across agents for budget management
tool-call-tracking
Instrument agent tool executions with proper context and error handling
effect-time-tracing-logging
Time with Clock/Duration, tracing spans, and structured logging. Use for time-based logic, deadlines, and observability.
ct-debug-skill
Debug and troubleshoot claude-threads, orchestrator, and agent issues
session-reflection-analysis
Use when asked to reflect on how the session went
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。