
Stop guessing at fixes. A 4-phase root-cause discipline (reproduce → isolate → hypothesize → verify) that forces your coding agent to find the real cause before touching code. The most-copied debugging skill in the Agent Skills ecosystem.
/systematic-debugging My checkout API returns 500, but only when two users pay at the same time
What you get
- A 4-phase root-cause protocol (reproduce, isolate, hypothesize, verify) your agent follows before writing any fix
- Rules that stop symptom fixes and speculative patches
- Techniques for flaky and intermittent failures
- Condition-based waiting patterns (with a TypeScript example)
Good fit
- Any bug, test failure, or unexpected behavior
- Flaky tests and intermittent production issues
- Bugs that already survived one "quick fix"
Not for
- Greenfield feature work (use test-driven-development)
- Performance profiling (use diagnosing-bugs)
- Repository
- obra/superpowers
- Stars
- 0
- Category
- Coding
- Skills inside
- 1
Exclusive content
Hosted on SkillStack — full markdown, yours after purchase.
--- name: systematic-debugging description: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes ---
Systematic Debugging
Overview
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
**Violating the…
Unlock the full content
Buy it once and keep it forever, or subscribe for access to everything.
Premium subscribers get this included.
Download & install
What's new: Initial SkillStack curated release: original MIT-licensed content repackaged as an install-ready ZIP with attribution.
Free for signed-in users.
1. Download the ZIP
Use the button above to download the packaged skill. It contains the SKILL.md plus all supporting files.
2. Unzip into your agent's skills folder
Extract the archive so that SKILL.md sits directly inside a folder named after the skill:
unzip systematic-debugging-v1.0.0.zip -d ~/.claude/skills/systematic-debugging/Skills folder per agent
- Claude Code
- ~/.claude/skills
- Cursor
- ~/.cursor/skills
- Codex
- ~/.codex/skills
- GitHub Copilot
- ~/.copilot/skills
3. Restart your agent
Your agent picks up the new skill automatically on next launch. Ask it what it can do.
FAQ
Is this one of Matt Pocock's agent skills?
Not directly — this skill comes from the obra/superpowers lineage, a different branch of the same Agent Skills movement Matt Pocock helped popularize. If you're specifically after his approach, our guide Matt Pocock's Agent Skills, Explained walks through his collection; the closest skill in his collection is diagnosing-bugs.
Reviews
Related skills
Diagnosing Bugs
mattpocock/skills
A battle-tested diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test. Includes a human-in-the-loop helper script. From a working engineer's daily setup.
Claude Code · Codex · Cursor
Git Workflow & Versioning
addyosmani/agent-skills
Branch strategy, commit discipline, PR hygiene, and release versioning for agent-driven development. Keeps AI-generated changes manageable, reviewable, and reversible at high speed.
Claude Code · Codex · Cursor · Copilot +1
Code Review & Quality
addyosmani/agent-skills
Multi-axis code review with severity gates (Critical/High/Medium/Low) across correctness, readability, architecture, security, and performance. By Addy Osmani (Google Chrome). Nothing merges without a verdict.
Claude Code · Codex · Cursor · Copilot
Readonly Question
Readonly Question
Ask anything about a codebase without changing a single file. A read-only /question mode for coding agents: evidence with file and line numbers, a proposed diff that is written out but never applied, and a verifiable 'No files were changed' footer. Understand the code first — change it only when you explicitly say so.
Claude Code · Codex · Cursor · Copilot +3