Yeachan-Heo/debugv1.1

debug

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

global

0installs0uses—~275

v1.1Saved Apr 20, 2026

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

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

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

76/100

Grade

Good

Safety

Quality

Clarity

Completeness

Summary

A diagnostic skill for troubleshooting OMC (OpenAI Model Context) sessions and Claude-Code workflows. It guides agents through systematic evidence collection, root-cause analysis, and minimal corrective actions by inspecting logs, traces, state tools, and project memory.

Detected Capabilities

Read trace and state diagnostic toolsInspect project logs and memoryReproduce failing test cases or commandsDistinguish symptoms from root causesGenerate minimal corrective action recommendations

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

debug failing testdiagnose workflow errortroubleshoot session issueinvestigate runtime behaviorfind root cause

Use Cases

Diagnose failing tests or commands in an active session
Investigate unexpected agent behavior or workflow breakage
Isolate runtime errors before attempting fixes
Understand orchestration or hook-related failures
Troubleshoot confusing session state or context issues

Quality Notes

Clear, concise workflow with logical flow (read → inspect → reproduce → analyze → recommend)
Well-defined output structure (observed failure, hypothesis, evidence, next action) gives agent clear completion criteria
Rules section establishes useful guardrails: prefer evidence over guesses, avoid premature rewrites, acknowledge product bugs
Scope is appropriately bounded to diagnostic activities — no writes, no destructive operations, read-only inspection
Missing specific examples of how to interpret trace/state tool output would improve clarity
No documented limitations (e.g., 'does not fix app code' or 'limited to current session')
Does not explicitly list which tools are available or their expected output formats — agent must infer from context

Model: claude-haiku-4-5-20251001Analyzed: Apr 20, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Content updated

2026-04-20

Latest

v1.0

No changelog

2026-04-03

Add Yeachan-Heo/debug to your library and activate them in your IDE via MCP.

Get Started Free