Skip to content
Agentmart
Submit a tool

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Skill by tim-hub

IndexedMIT★ 1
Write a review

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/tim-hub-systematic-debugging

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

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use cases: testing

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
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/systematic-debugging

What's inside

Skill name
systematic-debugging
Description
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
License
MIT
Instructions
37 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (6)

  • SKILL.md
  • condition-based-waiting-example.ts
  • condition-based-waiting.md
  • defense-in-depth.md
  • find-polluter.sh
  • root-cause-tracing.md

SKILL.md (first lines)

# Systematic Debugging

## Find the root cause

1. Read the error and the full stack trace. Note line numbers, paths, and codes. The answer is often already in there.
2. Reproduce it. Establish the exact steps and whether it happens every time. Not reproducible means gather more data, not guess.
3. Check what changed — recent commits, new dependencies, config, environment.
4. In a system with multiple components, instrument every boundary before proposing anything: log what enters each component, what leaves it, and whether config and environment propagated. Run once, then read the evidence to find which layer breaks.
5. Trace the bad value backward — where it originated, what passed it in — until you reach the source. Fix there, not at the symptom.

## Compare against what works

6. Find similar working code in this codebase.
7. If you are applying a pattern, read the reference implementation completely. Skimming it produces bugs.
8. List every difference between the working case and the broken one, however small.

## Test one hypothesis

9. State it plainly: X is the root cause because Y.
10. Make the smallest change that tests it. One variable at a time.
11. If it did not work, form a new hypothesis. Do not stack another fix on top of the last one.
12. Say plainly when you do not understand something rather than proceeding as if you do.

## Fix at the source

13. Write a failing test that reproduces the bug, before fixing anything.
14. Make one change, at the root cause. No bundled refactoring, no while-I-am-here improvements.
15. Verify: the test passes, nothing else broke, the original symptom is gone.
16. Count your failed fixes. At three, stop fixing and question the architecture with your partner. Fixes that each surface a new problem somewhere else mean the design is wrong, not the hypothesis.

If investigation shows the cause is genuinely environmental, timing-dependent, or external, document what you ruled out, add appropriate handling and monitoring, and say so explicitly.

Terminal state: invoke test-driven-development to lock the fix in with a regression test.

Depth: root-cause-tracing.md, defense-in-depth.md, condition-based-waiting.md

From tim-hub/superpowers-slim, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Aug 3, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from tim-hub

Cite this page

systematic-debugging skill. Agent Mart. https://agentmart.dev/skills/tim-hub-systematic-debugging (last updated 2026-10-24)