Skip to content
Agentmart
Submit a tool

debug

Debugging workflow that MUST reproduce, investigate, fix, and verify unexpected behavior.

Skill by gc-victor

IndexedMIT★ 33
Write a review

Chalk Labs

Need help deploying debug?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/gc-victor-debug

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Debugging workflow that MUST reproduce, investigate, fix, and verify unexpected behavior.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/debug

What's inside

Skill name
debug
Description
Debugging workflow that MUST reproduce, investigate, fix, and verify unexpected behavior.
License
MIT
Instructions
72 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Debugging Through Investigation

Debug issues through systematic investigation. This skill MUST debug problems using evidence: reproduce the issue, investigate likely causes, fix the root cause, and verify the result. It SHOULD form explicit hypotheses, test them one by one, and stop to ask for help when reproduction or confirmation is not possible.

## Process

### Understand the issue

- Read relevant code first.
- Ask one question at a time if clarification is needed.
- Focus on expected behavior, actual behavior, reproduction steps, timing, and recent changes.

### Reproduce the issue

- Reproduce before investigating deeply.
- Run the failing test, command, or workflow when possible.
- If you cannot reproduce it, investigate why.
- Record the reproduction case so you can verify the fix later.

### Form hypotheses

- Propose 2-3 likely causes.
- For each, state likelihood and how to test it.
- Present them to the user and wait for input.

### Investigate

- Test hypotheses one by one.
- Read the relevant code paths.
- Check logs, state, and execution flow.
- When you find the root cause, present it clearly and wait for confirmation.

### Fix

- Propose the fix before applying it.
- Make the smallest change that solves the root cause.
- Add a regression test when appropriate.

### Verify

- Re-run the reproduction case.
- Run the relevant tests.
- Check nearby functionality for similar failures.

## Report

Summarize:

- issue,
- root cause,
- fix,
- files changed,
- verification.

## Key Principles

- One question at a time
- Reproduce first
- Follow evidence, not guesses
- Fix the root cause, not the symptom
- Verify thoroughly

## When to Stop

Ask the user for help if:

- you cannot reproduce the issue,
- the fix needs domain knowledge you do not have,
- the change requires a broad architectural decision,
- multiple theories stay equally plausible.

From gc-victor/supersimple, MIT.

Signals

Stars
33
Forks
0
Open issues
0
Last commit (this folder)
Apr 30, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from gc-victor

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get debug running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying debug?

CallGet help
Cite this page

debug skill. Agent Mart. https://agentmart.dev/skills/gc-victor-debug (last updated 2026-10-24)