debugger SKILL.md skillA

debugger from claude-world/director-mode-lite is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add claude-world/director-mode-lite/debugger@git:20260831.099306a

Pins git:20260831.099306a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
claude-world/director-mode-lite
Path
skills/debugger/SKILL.md
Versions recorded
4
Latest version
git:20260831.099306a, committed Aug 31, 2026
First version recorded
Jan 16, 2026
Size
3,591 bytes
Repository stars
80
License
MIT

Systematic debugging method: 5-step root-cause analysis (capture, isolate, hypothesize, investigate, fix & verify) plus common bug-pattern reference. Use when errors, exceptions, test failures, or unexpected behavior appear. Loaded automatically by the debugger agent.

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

# Debugger Skill

> **Director Mode Lite** - Debugging Specialist

---

## 5-Step Root-Cause Method

```
1. CAPTURE      → Collect the full error, reproduce, define expected vs actual
2. ISOLATE      → Narrow to the smallest failing case
3. HYPOTHESIZE  → List and rank likely causes
4. INVESTIGATE  → Test hypotheses, inspect state
5. FIX & VERIFY → Apply the minimal fix, confirm, prevent recurrence
```

## Step 1: Capture

- [ ] Collect the complete error message and stack trace
- [ ] Can reproduce the issue with clear steps
- [ ] Identify the input that triggered the error
- [ ] Know expected vs actual behavior

## Step 2: Isolate

- [ ] Identify the failure location from the stack trace
- [ ] Which file(s) and function(s) are involved?
- [ ] When did it start? (`git bisect`, `git log`)
- [ ] Narrow down to the smallest reproducible case

## Step 3: Hypothesize

- [ ] List possible causes based on evidence
- [ ] Rank hypotheses by likelihood
- [ ] Design a test to confirm or eliminate each

## Step 4: Investigate

- Analyze error messages and logs carefully
- Add strategic debug logging; inspect variable state at key points
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add claude-world/director-mode-lite/debugger@sha256:09f3f50a8faf4074

The line at the top of this page pins the label git:20260831.099306a, 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 badge

[![mdr](https://markdownregistry.com/badge/art_j5rr7xzmuyv2ti6k.svg)](https://markdownregistry.com/a/art_j5rr7xzmuyv2ti6k)

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

Versions

The registry has recorded 4 versions of this file, between Jan 16, 2026 and Aug 31, 2026, about one every 76 days.

versioncommittedcommitsizeaudit
git:20260831.099306a latest2026-08-31 099306a 3,591 BA view · diff
git:20260706.14c55532026-07-06 14c5553 3,651 BA view · diff
git:20260116.9a229c02026-01-16 9a229c0 2,331 BA view · diff
git:20260116.d89779c2026-01-16 d89779c 2,352 BA 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 (3591 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

claude-world/director-mode-lite · 80 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_j5rr7xzmuyv2ti6k
GET https://markdownregistry.com/api/v1/resolve?ref=claude-world/director-mode-lite/debugger
GET https://markdownregistry.com/api/v1/blob/09f3f50a8faf407477008538a2207a8ff67f889ab060f0491d448ff7228b3557

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 claude-world/director-mode-lite

changelog-observer SKILL.md skill
claude-world/director-mode-lite · .claude/skills/changelog-observer/SKILL.md · Track development session events in a daily markdown changelog, including file changes, test results, and key decisions.
git:20260313.0818696 · audit A · 80 stars
CLAUDE.md@examples/01-calculator CLAUDE.md file
claude-world/director-mode-lite · examples/01-calculator/CLAUDE.md
git:20260111.3a91369 · audit A · 80 stars
CLAUDE.md@examples/02-rest-api CLAUDE.md file
claude-world/director-mode-lite · examples/02-rest-api/CLAUDE.md
git:20260111.8001004 · audit A · 80 stars
CLAUDE.md@examples/03-cli-tool CLAUDE.md file
claude-world/director-mode-lite · examples/03-cli-tool/CLAUDE.md
git:20260325.651d17a · audit A · 80 stars
CLAUDE.md@examples/04-library CLAUDE.md file
claude-world/director-mode-lite · examples/04-library/CLAUDE.md
git:20260325.651d17a · audit A · 80 stars
agent-check SKILL.md skill
claude-world/director-mode-lite · skills/agent-check/SKILL.md · Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent…
git:20261021.8facda8 · audit A · 80 stars
agent-template SKILL.md skill
claude-world/director-mode-lite · skills/agent-template/SKILL.md · Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with…
git:20261021.8facda8 · audit A · 80 stars
agents SKILL.md skill
claude-world/director-mode-lite · skills/agents/SKILL.md · List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs…
git:20260706.14c5553 · audit A · 80 stars
auto-loop SKILL.md skill
claude-world/director-mode-lite · skills/auto-loop/SKILL.md · TDD-based autonomous development loop with checkpoint recovery and observability changelog
git:20260706.14c5553 · audit A · 80 stars
changelog SKILL.md skill
claude-world/director-mode-lite · skills/changelog/SKILL.md · View and manage the runtime changelog for observability
git:20260726.87fe1ac · audit A · 80 stars
check-environment SKILL.md skill
claude-world/director-mode-lite · skills/check-environment/SKILL.md · Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks…
git:20261021.8facda8 · audit A · 80 stars
claude-md-check SKILL.md skill
claude-world/director-mode-lite · skills/claude-md-check/SKILL.md · Validate CLAUDE.md structure and completeness
git:20260116.d89779c · audit A · 80 stars

Every file in claude-world/director-mode-lite

Other files named debugger

debugger SKILL.md skill
antonbabenko/deliberation · .agents/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 177 stars
debugger SKILL.md skill
antonbabenko/deliberation · .gemini/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 177 stars
debugger SKILL.md skill
antonbabenko/deliberation · plugins/deliberation/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 177 stars
debugger SKILL.md skill
dhaupin/vant · models/public/vant/skills/vant-skill-debugger/SKILL.md · Debugging tools.
v1.0 · audit A · 12 stars
debugger SKILL.md skill
hybridlabor-api/bdb-dev-optimized-agent-skills · skills/global_config/debugger/SKILL.md · Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
git:20260912.e168019 · audit A · 6 stars
debugger SKILL.md skill
hybridlabor-api/aos · skills/global_config/debugger/SKILL.md · Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
git:20260912.e168019 · audit A · 6 stars

Browse by kind, by grade A, or by owner.