debug SKILL.md skillA

debug from qa-aman/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add qa-aman/claude-skills/debug@git:20260303.09b1726

Pins git:20260303.09b1726 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: qa-aman/claude-skills
Path: skills/by-role/engineer/debug/SKILL.md
Versions recorded: 1
Latest version: git:20260303.09b1726, committed Mar 3, 2026
Size: 3,790 bytes
Repository stars: 21
License: MIT

Debug a bug or unexpected behavior systematically. Use when the user says "there's a bug", "this isn't working", "I'm getting an error", "help me debug", "why is this failing", "unexpected behavior", "test is failing", "something is broken", or describes behavior that doesn't match expectations - even if they don't say "debug".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

## Overview

Based on **"The Pragmatic Programmer"** by Andrew Hunt & David Thomas. Hunt & Thomas's debugging philosophy: debugging is a puzzle to be solved with evidence, not a crisis to be panicked through. The key discipline is don't guess. Form a hypothesis, predict what you'll see if the hypothesis is correct, test it, and observe. Repeat.

Their rubber duck principle: before asking for help, explain the problem out loud (to a rubber duck or anyone). The act of articulating often reveals the answer.

## Workflow

### Step 1: Reproduce the bug reliably
You cannot debug what you cannot reproduce.
- What exact steps produce the bug? Document them.
- Is it 100% reproducible or intermittent?
- On which environments? (dev only, staging, prod?)
- Since when? (what changed recently?)

If you can't reproduce it reliably, make that the first problem to solve.

### Step 2: Understand the expected vs actual behavior
State explicitly:
- Expected: what should happen?
- Actual: what is happening?
- Evidence: logs, error messages, screenshots

Do not skip this. Vague bug descriptions lead to fixing the wrong thing.

### Step 3: Form a hypothesis
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add qa-aman/claude-skills/debug@sha256:d881e3e0e80eb506

The line at the top of this page pins the label git:20260303.09b1726, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_aj4cxqaqgdjbm6q4.svg)](https://markdownregistry.com/a/art_aj4cxqaqgdjbm6q4)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Mar 3, 2026.

version	committed	commit	size	audit
git:20260303.09b1726 latest	2026-03-03	09b1726	3,790 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3790 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

qa-aman/claude-skills · 21 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_aj4cxqaqgdjbm6q4
GET https://markdownregistry.com/api/v1/resolve?ref=qa-aman/claude-skills/debug
GET https://markdownregistry.com/api/v1/blob/d881e3e0e80eb506936c0b11a4f28a4b044e3a2873e965f80c418b93cd8a9512

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from qa-aman/claude-skills

create-skill SKILL.md skill

qa-aman/claude-skills · .claude/skills/create-skill/SKILL.md · Create or update Claude Code skills following Anthropic's official skill standard. Use when user says "create a skill"…

git:20260303.4fa499f · audit A · 21 stars

sync-skills SKILL.md skill

qa-aman/claude-skills · .claude/skills/sync-skills/SKILL.md · Fetch skills from projects on the current system, genericize them, and add to the claude-skills repository. Use when…

git:20260303.4fa499f · audit A · 21 stars

CLAUDE.md CLAUDE.md file

qa-aman/claude-skills · CLAUDE.md

git:20260808.3d6e28d · audit A · 21 stars

audit-workpaper SKILL.md skill

qa-aman/claude-skills · skills/by-role/accountant/audit-workpaper/SKILL.md · Write a clear, reviewable audit workpaper documenting procedures, evidence, and conclusions. Use when an auditor says…