Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

debug · yeachan-heo — Claude Code skill: what it does, how to install

Diagnoses broken OMC sessions, workflow failures, and repo state issues using traces and targeted reproduction.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add Yeachan-Heo/oh-my-claudecode --skill debug -a claude-code
Open on GitHub

What debug does

The skill tracks down runtime failures and orchestration issues in oh-my-claudecode sessions. It inspects local evidence first: trace logs, state tools, project memory, and failing test commands, prioritizing facts over assumptions.

Broad rewrites before isolating the failure are explicitly forbidden. Temporary diagnostic prints get marked with a [DEBUG-<4hex>] tag. Cleanup needs just one grep. Sensitive data and credentials are scrubbed from logs before leaving the session.

The resulting report outlines the observed failure, a root-cause hypothesis backed by evidence, and the smallest corrective step. If an architectural seam is broken, the skill points directly to refit or architecture-survey.

What it helps with

  • isolate orchestration breakdowns across hooks and agents
  • separate surface symptoms from the root cause
  • clean up temporary debug output using grep tags
  • redact credentials from logs before sharing

Example prompts for the agent

  • Diagnose why the agent hook broke during this session
  • Find the root cause of this test failure using session traces
  • Investigate confusing runtime behavior without rewriting existing code

How to install debug

1Skills CLI (Vercel)

npx skills add Yeachan-Heo/oh-my-claudecode --skill debug -a claude-code

2Manually: put the files in place

~/.claude/skills/debug/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/debug/

From the same set26

The whole set →
ai-slop-cleaner Yeachan-Heo Cleans bloated AI-generated code by deleting dead logic and duplicate abstractions. It keeps current behavior locked under regression tests. Claude Code CX Codex Cursor +1 1,500installs ralplan Yeachan-Heo A skill that runs iterative planning with three agents (Planner, Architect, Critic) until consensus. Blocks vague requests before execution, never runs changes without your approval. Claude Code CX Codex Cursor +1 1,200installs hud Yeachan-Heo The hud skill configures a HUD display in Claude Code's statusline, showing git branch, context usage, running subagents, and other metrics. Track session state and keep tabs on complex work without losing context. Claude Code CX Codex Cursor +1 1,100installs deepinit Yeachan-Heo Walks a repository and writes an AGENTS.md per directory: what sits there, how the parts connect, what an agent should know before editing. Claude Code CX Codex Cursor +1 1,000installs autopilot Yeachan-Heo A skill that takes a task description and runs the full development cycle: requirements analysis, design, implementation, testing, and validation—all hands-off. Use it when you want to describe what you need and get working code back. Claude Code CX Codex Cursor +1 999installs deep-interview Yeachan-Heo A skill that runs a Socratic interview on your idea, scores ambiguity across weighted dimensions, and blocks coding until the score falls under the threshold. Claude Code CX Codex Cursor +1 998installs omc-setup Yeachan-Heo Canonical setup and repair wizard for oh-my-claudecode. It configures CLAUDE.md files, HUD statusline, and agent team defaults. Claude Code CX Codex Cursor +1 987installs ralph Yeachan-Heo A persistence loop that works through tasks in prd.json until all stories pass and get reviewer verification. Useful for multi-step jobs that need guaranteed completion. Claude Code CX Codex Cursor +1 971installs

Other versions of debug

debug official anthropics This skill takes a bug from reproduction to root cause, a fix, and regression coverage. Use it when the symptom is clear but the cause is not. Claude Code CX Codex Cursor +1 5,800installs

Similar

agent-tool-builder sickn33 A skill for writing tool schemas an agent can actually use: JSON Schema, descriptions, validation, error paths. Useful when it keeps calling the wrong function. Claude Code CX Codex Cursor +1 958installs vector-hyperbolic ruvnet Places hierarchical data in the Poincaré ball: radius from tree depth, direction from a text embedding. For dependency trees, ontologies, class hierarchies. Claude Code CX Codex Cursor +1 724installs convex-create-component convex A skill to design and build reusable Convex components with isolated tables and a clear API boundary. Useful when you need to extract backend logic into a self-contained module or package an integration that owns its own data. Claude Code CX Codex Cursor +1 130,600installs ce-pov EveryInc Forms a grounded verdict on whether an external solution, document, or approach fits your project. Judges only by evidence from your codebase and constraints. Claude Code CX Codex Cursor +1 1,000installs router gamedev-skills Dispatches game development tasks to specialized skills by detecting the project engine and classifying gameplay or shipping workflows. Claude Code CX Codex Cursor +1 6,400installs solid vercel-labs Skill to render JSON-specs into reactive SolidJS components. Use it when building UI catalogs, wiring providers, or debugging Solid reactivity patterns. Claude Code CX Codex Cursor +1 1,100installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about debug

How to install debug in Claude Code?

Run npx skills add Yeachan-Heo/oh-my-claudecode --skill debug -a claude-code in your terminal. You can also place it directly at ~/.claude/skills/debug/SKILL.md.

What does the debug skill do?

It analyzes traces, session state, and memory to uncover the real root cause of runtime errors, then recommends the smallest next fix.

How does the skill handle temporary log lines?

It tags temporary diagnostic output with [DEBUG-<4hex>], allowing you to clean up all temporary lines with a single grep command.

Source text

SKILL.md · MIT 
---
name: debug
description: Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
---

# 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

© Yeachan-Heo · MIT · Yeachan-Heo/oh-my-claudecode

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor