Trace
Orchestrates structured investigation: restate observations, generate competing hypotheses, gather evidence in parallel, rank explanations for ambiguous causal bugs.
npx skills add https://github.com/yeachan-heo/oh-my-claudecode --skill trace| Installs | 404 |
|---|---|
| Repository | yeachan-heo/oh-my-claudecode ↗ |
What it does
Developers waste time jumping to solutions without systematically ruling out alternative causes
Who is it for?
Diagnosing bugs where the cause is unclear and multiple competing theories exist
Skip if: Well-understood bugs with obvious fixes
When should I use this skill?
Root cause of an error is ambiguous and multiple competing theories exist
What you get
A ranked set of hypotheses with supporting evidence and a clear next investigative action
- ranked hypothesis list
- evidence summary
- recommended next investigation step
Related skills
Microsoft FoundryDeploy, invoke, evaluate, and troubleshoot Microsoft Foundry agents with Docker, ACR, and observability workflows.400k1.2kAzure AiWire Azure AI services—especially Content Safety in Java—into a solo builder’s backend when you need moderation, blocklists, and SDK patterns without digging through full Microsoft docs.397k1.2kAzure Hosted Copilot SdkDetect @github/copilot-sdk in a repo and scaffold, extend, or deploy Copilot-powered apps on Azure with BYOM support.369k1.2k
Lark EventRun long-lived Lark event consumers that stream IM, VC, and Minutes events as NDJSON for bots and agent subprocesses.244k
Setup Matt Pocock SkillsBootstrap AGENTS.md/CLAUDE.md and docs/agents/ with issue tracker, triage label vocabulary, and domain doc layout before using triage, PRD, TDD, and architecture skills.223k121k
Running Claude Code Via Litellm CopilotPoint Claude Code at a local LiteLLM proxy forwarding to GitHub Copilot Chat API for cheaper runs.220k61