Skip to content
Skills Library
Programming · Analysis

verify-debug-systematically

/verify-debug-systematically

Verify — Find the root cause of a bug, a failing test or unexpected behaviour before changing code, and stop after repeated failed fixes. Use when a test fails, something behaves unexpectedly or a bug is reported ("no funciona", "falla el test", "sigue fallando", "why does this break", "debug this"), when ai1/fix-loop says several fix attempts in a row have failed, or when the person says "deja de adivinar", "stop guessing", "¿estamos atascados?".

Repository
ai1 ↗
Licence
MIT
Last repository change
13.11.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Verify — Find the root cause of a bug, a failing test or unexpected behaviour before changing code, and stop after repeated failed fixes. Use when a test fails, something behaves unexpectedly or a bug is reported ("no funciona", "falla el test", "sigue fallando", "why does this break", "debug this"), when ai1/fix-loop says several fix attempts in a row have failed, or when the person says "deja de adivinar", "stop guessing", "¿estamos atascados?".

Triggers from the description

no funcionafalla el testsigue fallandowhy does this breakdebug thisdeja de adivinarstop guessing¿estamos atascados?
Original author description

Verify — Find the root cause of a bug, a failing test or unexpected behaviour before changing code, and stop after repeated failed fixes. Use when a test fails, something behaves unexpectedly or a bug is reported ("no funciona", "falla el test", "sigue fallando", "why does this break", "debug this"), when ai1/fix-loop says several fix attempts in a row have failed, or when the person says "deja de adivinar", "stop guessing", "¿estamos atascados?".

How it works

  1. 1. Investigate the cause
  2. 2. Compare with something that works
  3. 3. One hypothesis at a time
  4. 4. Fix with a test
  5. Red flags: go back to step 1
  6. After repeated failed fixes
  7. Fixed rules
  8. Customization
Original SKILL.md headings · 62 lines, 506 words
SKILL.md preview
---
name: verify-debug-systematically
description: Verify — Find the root cause of a bug, a failing test or unexpected behaviour before changing code, and stop after repeated failed fixes. Use when a test fails, something behaves unexpectedly or a bug is reported ("no funciona", "falla el test", "sigue fallando", "why does this break", "debug this"), when ai1/fix-loop says several fix attempts in a row have failed, or when the person says "deja de adivinar", "stop guessing", "¿estamos atascados?".
allowed-tools: Bash("${CLAUDE_PLUGIN_ROOT}/bin/ai1" skill-context *)
---

# Debug systematically

A fix without the cause is a guess, and guesses pile up: each one can hide the bug or move it. Find
the cause first; then one fix, proven by a test.

## 1. Investigate the cause

- Read the whole error: message, stack, the first failing assertion, not just the last line.
- Reproduce it reliably, with the smallest command (one test, one request). If it does not reproduce
  every time, that is a finding: look for timing, order or shared state.
- Check what changed: `git diff`, `git log -p` on the files involved, recent dependency updates.
- Trace the bad value back to where it is created, through each boundary (function, process, API,
  database), instead of patching where it shows up.

## 2. Compare with something that works

Find a similar case that works (another test, another input, the last good commit) and list every
difference. `git bisect` when a commit broke it.

## 3. One hypothesis at a time

Write it down in one sentence ("the cache keeps the old value because..."), make the smallest
change or measurement that can prove it wrong, and look. Wrong: drop it, back to step 1 with what
you learned. Several changes at once teach nothing.

## 4. Fix with a test

A test that fails for the reason found, then the fix, then the test passes, then the full suite.
Fix the cause, not the symptom; if the same bad input can come from elsewhere, check there too.

## Red flags: go back to step 1

| You are about to... | Instead |
|---|---|
| try a fix "to see if it works" | name the cause it addresses |
| change several things at once | one change, one check |
| skip the failing test | write it first |
| add a sleep or retry to a flaky test | wait for the condition the test needs (poll with a timeout) |
| try "one more" fix after two failed | stop and question the approach |

## After repeated failed fixes

After 3 failed attempts in a row (ai1/fix-loop counts them and tells you), stop patching. Each fix
that fails somewhere new points to a wrong assumption or a design problem, not a missing tweak. Tell
the person what you tried, what each attempt showed and what you now think the cause is, and agree
on the next step before another fix.

When the cause teaches something about the system (how a component really behaves, a trap), record
it in the knowledge bundle.

## Fixed rules

- No fix without a stated cause; no fix without a test that failed first.
- After 3 failed fix attempts in a row, stop and talk to the person before another fix.

## Customization

This project or the person may add their own rules below; they never override the fixed rules. If no `## ai1 customization` section follows, run `"${CLAUDE_PLUGIN_ROOT}/bin/ai1" skill-context verify-debug-systematically` and apply what it prints.

!`"${CLAUDE_PLUGIN_ROOT}/bin/ai1" skill-context verify-debug-systematically`

Versions

The database has no other skills named verify-debug-systematically.

Database snapshot: 13.11.2026 · package version d5fa5e528863 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100root-cause-debugging
    Debug by finding the root cause before changing code: reproduce, read the full error, check what changed, form one hypothesis at a time and test it, write the failing test, then fix; with a hard stop after three failed fixes to question the approach. Use when a test fails, a bug…
  • 90debugging
    Use for any bug, failing test, crash or unexpected behaviour, before proposing a fix. Root cause first, one hypothesis at a time, and a stop after three failed fixes.
  • 92debug
    Find the root cause of a bug before you fix it. Read this skill before you fix any bug. Read it also when the fix looks obvious. Use it when the user says "fix", "broken", "not working", "error", "failing", or "bug". Use it also when a test fails unexpectedly during other work.
  • 100sdlc-debug
    Bug track: reproduce, find the root cause with evidence, write a failing regression test, apply the smallest fix, check siblings, verify on the real surface. Use when something behaves wrongly, a test fails, an error is reported, or the user says 'debug', 'fix this bug' or 'why does X happen'.
  • 100debug-root-cause
    Systematically find and fix the root cause of bugs, errors, failing tests, and crashes in JavaScript/TypeScript and Python. Use whenever the user pastes an error or stack trace, says something is broken, "not working", "error", "kenapa gagal", "bug", a test fails, or behavior is…
  • 100systematic-debugging
    Debug a bug, test failure, crash, or unexpected behaviour by finding the root cause before changing anything, instead of guessing at fixes. Works in any language or stack. Use when something is broken, a test is failing, behaviour is wrong, or a previous fix didn't hold.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.