What does the debug skill do?

It lets an agent diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction.

When should the debug agent skill be used?

When a session behaves unexpectedly or a repository is in an unclear state and the cause is not obvious.

Does it modify the repo?

The item does not say. It is described as diagnosing state via logs, traces, and focused reproduction.

Debug

SkillMonitoring & ops

The debug skill is an agent skill for diagnosing the current OMC session or repository state. It lets an agent inspect logs, traces, and state, and run focused reproduction to find what is going wrong. The debug skill is useful when a session behaves unexpectedly or a repo is in an unclear state.

Use Debug in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Debug and connect your AI. About a minute.

Claude ChatGPT Ahel Desktop

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Debug skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

No other account needed.

Have an OMC session or repository to diagnose.

DebugStart free

What your AI can do with it

Diagnose the current OMC session state
Diagnose the current repo state
Inspect logs to find problems
Inspect traces to follow what happened
Inspect stored state
Run focused reproduction of an issue

Getting started

Have an OMC session or repository to diagnose.
Add the debug skill to the agent's available skills.
Ask the agent to diagnose the session or repo state using the skill.
Review the logs, traces, state findings, and reproduction results the agent reports.

What this skill tells your AI

The instructions your AI receives, as published by yeachan-heo/oh-my-claudecode in skills/debug/SKILL.md and read by ahel’s review.

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

Read the user’s issue description carefully.
Inspect the most relevant local evidence first:
- trace tools
- state tools
- notepad / project memory when relevant
- failing tests or commands
Reproduce the issue narrowly if possible.
Distinguish symptoms from root cause.
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.

Output

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

Signals

GitHub stars: 39k
Forks: 4k
Last commit: Oct 2026
Hacker News mentions: 20

Questions

What does the debug skill do?: It lets an agent diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction.
When should the debug agent skill be used?: When a session behaves unexpectedly or a repository is in an unclear state and the cause is not obvious.
Does it modify the repo?: The item does not say. It is described as diagnosing state via logs, traces, and focused reproduction.

Advanced

Item type: skill
Key: debug-yeachan-heo
Source: github.com/yeachan-heo/oh-my-claudecode

github.com/yeachan-heo/oh-my-claudecode

More in Monitoring & ops

internal-comms
Skill · anthropics
More in Monitoring & ops agent-eval
Skill · affaan-m
More in Monitoring & ops dashboard-builder
Skill · affaan-m
More in Monitoring & ops babysit
Skill · thedotmack
More in Monitoring & ops eng-runbook
Skill · nexu-io
More in Monitoring & ops weekly-update
Skill · nexu-io
More in Monitoring & ops