Skip to content
Agentmart
Submit a tool

systematic-debugging

Root-cause a failure with an evidence-first loop (reproduce, one hypothesis, minimal probe, smallest fix, re-run).

Skill by mimimaster

IndexedMIT★ 142
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/mimimaster-systematic-debugging-d2614a

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

Root-cause a failure with an evidence-first loop (reproduce, one hypothesis, minimal probe, smallest fix, re-run). Use before proposing a fix for any bug, failing test, crash, error message, build or typecheck failure, or unexpected behavior (报错 / 不工作 / 挂了).

Use cases: testing

Reviews

Write a review

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/systematic-debugging

What's inside

Skill name
systematic-debugging
Description
Root-cause a failure with an evidence-first loop (reproduce, one hypothesis, minimal probe, smallest fix, re-run). Use before proposing a fix for any bug, failing test, crash, error message, build or typecheck failure, or unexpected behavior (报错 / 不工作 / 挂了).
License
MIT
Instructions
24 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Systematic Debugging

## Goal
A root-caused, minimal fix for a reproduced failure, with evidence it no longer fails.

## Done means
- Failure is reproduced with exact command, error text, and environment notes.
- Smallest failing surface is identified (file, test, log line).
- One falsifiable hypothesis was tested with a minimal probe (log, assertion, or failing test).
- Smallest fix that passes the probe is in place.
- Original failing path plus one nearby regression check pass.
- Root cause is recorded briefly for the next agent/PR.

## Stop when
- Cannot reproduce — gather more evidence; do not shotgun-edit.
- Hypothesis disproved — form the next single hypothesis; do not stack unrelated changes.

## Constraints
- No “fixed” claim without re-run evidence in this environment.

## Verify
- Failing path is green after the fix; probe/test remains as lasting signal when useful.

From mimimaster/piwin, MIT.

More from mimimaster/piwin

Signals

Stars
142
Forks
6
Open issues
0
Last commit (this folder)
Sep 17, 2026 (1 month ago)
Last release
Oct 8, 2026 (21 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/mimimaster/piwin
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from mimimaster

Cite this page

systematic-debugging skill. Agent Mart. https://agentmart.dev/skills/mimimaster-systematic-debugging-d2614a (last updated 2026-10-24)