StealIt

Systematic Debugging

systematic-debugging

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

Install

Run this in your project folder. It works with Claude Code, Cursor, Codex and dozens of other agents.

$ npx skills add obra/superpowers --skill systematic-debugging

Needs Node.js. Add -g to install for every project, or -a claude-code to skip the agent picker.

How to use Systematic Debugging

Once it's installed, Claude reads this skill on its own whenever a request matches what it's for, so you don't have to mention it by name. In Claude Code you can also run it directly by typing /systematic-debugging.

It includes scripts that Claude may run on your computer, so skim them on GitHub before you install.

What the instructions cover

  1. 1Overview
  2. 2The Iron Law
  3. 3When to Use
  4. 4The Four Phases
  5. 5Red Flags - STOP and Follow Process
  6. 6your human partner's Signals You're Doing It Wrong
  7. 7Common Rationalizations
  8. 8Quick Reference
  9. 9When Process Reveals "No Root Cause"
  10. 10Supporting Techniques

Section headings from the skill's SKILL.md file.

What's inside · 6 files

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

More from Jesse Vincent

See all →

BrainstormingTop pick

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it…

Coding WorkflowJesse Vincent312k

Diagnosing Superpowers

Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too…

Coding WorkflowJesse Vincent312k

Dispatching Parallel Agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

AI & AgentsJesse Vincent312k

Executing Plans

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

Coding WorkflowJesse Vincent312k
See all →

Grill MeTop pick

A relentless interview to sharpen a plan or design.

Coding WorkflowMatt Pocock313k

CavemanTop pick

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop…

Coding WorkflowJulius Brussee117k

PonytailTop pick

Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring…

Coding WorkflowDietrich Gebert184k

Ponytail Audit

Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding…

Coding WorkflowDietrich Gebert184k