Agent Skill

Systematic Debugging skill

systematic-debuggingSuperpowersskills/systematic-debugging/SKILL.md

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

303kMIT

always on

21 tokname + description

once used

2,175 tokSKILL.md body

bundled files

102 scripts

installs

303kskills.sh

Install the Systematic Debugging skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/obra/superpowers --skill systematic-debugging

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/obra/superpowers.git /tmp/superpowers
mkdir -p ~/.claude/skills
cp -R /tmp/superpowers/skills/systematic-debugging ~/.claude/skills/systematic-debugging

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	21 tok
When the agent uses it	The SKILL.md instructions	2,175 tok
Only if opened	10 bundled files (31 KB)	varies

Until it is used, systematic-debugging costs about 65× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 15 skills from obra/superpowers would load 489 tokens of descriptions. Skills vs MCP study

Checks

Ships scripts the agent can run. Read them before installing.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

Systematic Debugging
Overview
The Iron Law
When to Use
The Four Phases
Phase 1: Root Cause Investigation
Phase 2: Pattern Analysis
Phase 3: Hypothesis and Testing
Phase 4: Implementation
Red Flags - STOP and Follow Process
your human partner's Signals You're Doing It Wrong
Common Rationalizations
Quick Reference
When Process Reveals "No Root Cause"
Supporting Techniques

More skills from obra/superpowers

All skills in this repo

brainstormingobra/superpowers
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 (a talk, a business, a renovation).
401k446 tok idle · 3,062 in use
writing-plansobra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
281k21 tok idle · 2,284 in use
using-superpowersobra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
269k28 tok idle · 700 in use
requesting-code-reviewobra/superpowers
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
260k22 tok idle · 660 in use
test-driven-developmentobra/superpowers
Use when implementing any feature or bugfix, before writing implementation code
257k17 tok idle · 2,316 in use
verification-before-completionobra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
249k43 tok idle · 803 in use
executing-plansobra/superpowers
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
241k35 tok idle · 4,228 in use
subagent-driven-developmentobra/superpowers
Use when executing implementation plans with independent tasks in the current session
235k17 tok idle · 4,404 in use