Skip to content
Back to skills

Debug

ASecurity

Systematically analyze and fix a bug. Uses hypothesis-driven debugging, records the process in spec/DEBUG.md, and updates spec/STATE.md on resolution.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added May 27, 2026
data-aidebugging

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add ByeongminLee/nextjs-claude-code --skill debug --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Debug?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Debug
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/byeongminlee-debug/badge)](https://www.skillsdirectory.com/skills/byeongminlee-debug)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: debug
description: Systematically analyze and fix a bug. Uses hypothesis-driven debugging, records the process in spec/DEBUG.md, and updates spec/STATE.md on resolution.
argument-hint: "[bug symptom or description]"
context: fork
---

## Model selection

Assess task size per `spec/rules/_model-routing.md`:
- If the bug description references a single file or a clear, localized symptom → spawn `debugger` with `model: haiku`
- If the bug is cross-feature, involves unclear reproduction, or could have multiple root causes → spawn `debugger` with `model: sonnet`
- If unsure → default to `model: sonnet`

## Task

Spawn `debugger` agent (with assessed model) with the following prompt:

```
Analyze and fix the following bug:
$ARGUMENTS
```

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…