Trace
技能 已验证 活跃Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode
To provide an evidence-driven tracing lane that orchestrates competing tracer hypotheses, aiding in the explanation of 'why' observed results occurred.
功能
- Orchestrates competing tracer hypotheses
- Gathers evidence in parallel
- Ranks hypotheses and proposes next probes
- Supports runtime bugs, performance, and architecture analysis
使用场景
- Tracing runtime bugs and regressions
- Explaining performance, latency, or resource behavior
- Conducting architecture, premortem, or postmortem analysis
- Tracing scientific or experimental results
非目标
- Collapsing into a generic fix-it coding loop
- Providing a generic debugger summary
- Dumping raw worker output
- Claiming fake certainty when evidence is incomplete
安装
请先添加 Marketplace
/plugin marketplace add Yeachan-Heo/oh-my-claudecode/plugin install oh-my-claudecode@omc质量评分
已验证类似扩展
LangSmith Observability
99LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
Project Development
100This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.
Write A Skill
100Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Extract
100Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
使用我的浏览器
100当工作依赖于用户实时浏览器会话或可见的渲染状态，而不是静态抓取时使用，尤其是在浏览器调试上下文或 DevTools 选择的元素或请求、登录仪表板或 CMS 流程、localhost 应用、上传、下载、媒体检查、DOM 或 iframe 检查、Shadow DOM，或看起来像软 404、身份验证墙、反机器人检查或速率限制的浏览器故障时。