Skip to content
Skills Library
Programming · Analysis

systematic-debug

/systematic-debug

Four-step root-cause protocol for bugs, regressions, defects that came back after a fix, or behaviour only seen on a device or video. Use when the cause is not obvious, when one fix already failed, or when the report is only a symptom.

Licence
MIT
Last repository change
12.11.2026

Assessment and security

86/ 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.
Content21 / 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 12.11.2026, 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

Four-step root-cause protocol for bugs, regressions, defects that came back after a fix, or behaviour only seen on a device or video. Use when the cause is not obvious, when one fix already failed, or when the report is only a symptom.

Original author description

Four-step root-cause protocol for bugs, regressions, defects that came back after a fix, or behaviour only seen on a device or video. Use when the cause is not obvious, when one fix already failed, or when the report is only a symptom.

How it works

SKILL.md has no level-two headings · 12 lines, 211 words

SKILL.md preview
---
name: systematic-debug
description: Four-step root-cause protocol for bugs, regressions, defects that came back after a fix, or behaviour only seen on a device or video. Use when the cause is not obvious, when one fix already failed, or when the report is only a symptom.
---

# Systematic debugging

Guessing costs hours; root cause costs minutes. Detail: `docs/agents/standard/MODES.md#fixer`, project rework ledger.

1. **Boundaries.** Where the data/behaviour enters, leaves, and every independent driver in between (UI, state, API, auth/RLS, worker, native view, timer, animation, layout pass). Which side is wrong?
2. **Reproduce and instrument.** Failing test, capture, or probes that print numbers at the boundaries. No reproduction, no root cause. Tests must never fake an event the platform does not emit.
3. **Isolate.** The surviving hypothesis explains **all** symptoms, including ones not reported. "Worked before" → `git log -S` / bisect. Library involved → read the installed version's source. Same pattern elsewhere? Remove probes afterwards.
4. **One owner, one fix.** Smallest change; one module owns the behaviour (delete competing paths); the failing test now passes; neighbours unchanged; canonical checks green; guard added; ledger row updated.

Rules: **two failed attempts = stop**, bring evidence and a recommendation, never a third attempt of the same kind. One round = one root cause; other bugs go to a list. Owner-reported bug: present cause + planned change and wait for approval before editing. A defect that appears *during* an approved task and is small and in scope: fix it without asking (skill `self-heal`); this protocol takes over from its second failed attempt.

Versions

RepositoryScoreLicence
This page · lucasouzadev/agent-kit-skill86MIT
xoai/sage100MIT
xbklairith/kisune100MIT
mtvrkan/senior-dev-kit100MIT
skymanbp/cc-enforcer90MIT

Database snapshot: 13.11.2026 · package version bbd5af428a24 (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

  • 100systematic-debugging
    Find the root cause of a bug, test failure, crash or unexpected behaviour before changing any code. Use this whenever something does not work as expected, a test fails, an error appears, or an earlier fix did not hold, even when the cause looks obvious, because the obvious cause is often a symptom.
  • 100systematic-debugging-codex
    Systematic 4-phase debugging with Codex-backed root cause investigation. Use only when the user explicitly asks for the Codex-backed debugging workflow.
  • 100systematic-debugging
    Diagnoses a reported bug, error, test failure, or unexpected behavior through a 4-phase root-cause analysis before any code changes. Use when the user reports a bug or test failure with an unknown root cause, or invokes /superpowers:systematic-debugging "<symptom>". Not for bugs…
  • 95community-systematic-debugging
    Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
  • 90debug-to-root-cause
    Use whenever something is broken, flaky, or behaving unexpectedly — find the root cause systematically (reproduce, isolate, hypothesize, verify) and fix the cause, not the symptom. Never shotgun-edit.
  • 81debug
    Use when encountering any bug, test failure, build break, or unexpected behavior — runs a 4-phase systematic debugging process before proposing any fix. Iron Law: NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Produces a `.orchestrator/debug/` artifact the fixer agent must reference.

Feedback and reports

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