# debugging

Enforces a disciplined debugging methodology that stops guesswork and requires fresh test proof before marking tasks done.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 569 installs · ★ 2228
- Author: mrgoonie
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/debugging/SKILL.md
- Updated: 2026-04-03
- HTML: https://affpapa.org/en/nevibecode/skills/mrgoonie-debugging

## What it does

The skill replaces trial-and-error patching with a structured investigation workflow. It organizes debugging into four sub-skills: systematic investigation, root-cause tracing, defense-in-depth validation, and mandatory post-fix verification.

Under these rules, an assistant cannot jump straight into editing code. It must investigate the root failure and track invalid inputs to their origin. The framework explicitly forbids declaring success without running verification commands and inspecting output.

This strict sequence prevents masking symptoms with temporary workarounds. According to the author, structured debugging achieves a 95% first-time fix rate compared to 40% when thrashing with random changes.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mrgoonie/claudekit-skills --skill debugging -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/debugging/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/debugging/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mrgoonie/claudekit-skills --skill debugging -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/debugging/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mrgoonie/claudekit-skills --skill debugging -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/debugging/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mrgoonie/claudekit-skills debugging
```

2. **Manually: put the files in place**
- File: `.github/skills/debugging/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mrgoonie/claudekit-skills --skill debugging -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mrgoonie/claudekit-skills --path .claude/skills/debugging
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/debugging/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add mrgoonie/claudekit-skills --skill debugging -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mrgoonie/claudekit-skills/tree/HEAD/.claude/skills/debugging/SKILL.md

## When to use it
- trace root causes backward through complex call stacks
- stop the agent from applying random trial-and-error fixes
- prevent recurring regressions across multiple application layers
- verify bug fixes with fresh command execution before completion

## Example prompts
- Use root-cause-tracing to find where this invalid payload originated in the stack
- Apply systematic-debugging to investigate the auth test failure
- Run verification-before-completion checks before marking this bug resolved

## Similar
- [systematic-debugging](https://affpapa.org/en/nevibecode/skills/spencerpauly-systematic-debugging.md) — skill · 545 installs
- [debugging-and-error-recovery](https://affpapa.org/en/nevibecode/skills/debugging-and-error-recovery.md) — skill · 62800 installs
- [debugger](https://affpapa.org/en/nevibecode/agents/debugger.md) — subagent · 13459 installs
- [debugging-network-issues](https://affpapa.org/en/nevibecode/skills/debugging-network-issues.md) — skill · 675 installs
- [debugging-strategies](https://affpapa.org/en/nevibecode/skills/debugging-strategies.md) — skill · 13414 installs
- [principle-prove-it-works](https://affpapa.org/en/nevibecode/skills/principle-prove-it-works.md) — skill · 5200 installs

## Other versions with the same name
- [debugging · tursodatabase](https://affpapa.org/en/nevibecode/skills/debugging.md) — 1300 installs
- [debugging · akillness](https://affpapa.org/en/nevibecode/skills/akillness-debugging.md) — 361 installs

From the same set: [mrgoonie/claudekit-skills](https://affpapa.org/en/nevibecode/by/mrgoonie/claudekit-skills.md) — 21 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md