# Debug

> Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

- Skill: `tuyv/debug-3` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx get-skill add tuyv/debug-3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tuyv/debug-3/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tuyv (https://skillmd.com/u/tuyv)
- Updated: 2026-11-14
- Page: https://skillmd.com/skills/tuyv/debug-3

---


# Debug

Use this skill when the user wants help diagnosing a current OMC/Claude-Code session problem, workflow breakage, or confusing runtime behavior.

## Goal
Find the real failure signal quickly and explain the next corrective step.

## Workflow
1. Read the user’s issue description carefully.
2. Inspect the most relevant local evidence first:
   - trace tools
   - state tools
   - notepad / project memory when relevant
   - failing tests or commands
3. Reproduce the issue narrowly if possible.
4. Distinguish symptoms from root cause.
5. Recommend the smallest next fix or verification step.

## Rules
- Prefer real evidence over guesses.
- Use the trace/state surfaces when the issue involves orchestration, hooks, or agent flow.
- If the issue is actually a product/runtime bug rather than app code, say so plainly.
- Do not prescribe broad rewrites before isolating the failure.
- Tag temporary debug output `[DEBUG-<4hex>]`; cleanup is then a single grep.
- Redact secrets from logs and traces before they leave the session.
- If the failure traces to a missing or wrong seam, say so as the finding and point at `refit` or `architecture-survey` — the environment lesson outlives the fix.

## Output
- Observed failure
- Root-cause hypothesis
- Evidence for that hypothesis
- Smallest next action


