Babysitter systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause investigation first.

install

source · Clone the upstream repo

git clone https://github.com/a5c-ai/babysitter

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/superpowers/skills/systematic-debugging" ~/.claude/skills/a5c-ai-babysitter-systematic-debugging-33e286 && rm -rf "$T"

manifest: library/methodologies/superpowers/skills/systematic-debugging/SKILL.md

Systematic Debugging

Overview

Random fixes waste time and create new bugs. ALWAYS find root cause before attempting fixes.

Core principle: No fixes without root cause investigation first.

The Four Phases

Root Cause Investigation - Read errors, reproduce, check changes, gather evidence at component boundaries
Pattern Analysis - Find working examples, compare against references, identify differences
Hypothesis and Testing - Form single hypothesis, test minimally, one variable at a time
Implementation - Create failing test case, implement single fix, verify

When 3+ Fixes Fail

Stop and question the architecture. Pattern of repeated failures indicates architectural problems, not implementation bugs.

Red Flags (STOP and Follow Process)

"Quick fix for now"
"Just try changing X"
Proposing solutions before tracing data flow
"One more fix attempt" (when already tried 2+)

Agents Used

Process agents defined in
```
systematic-debugging.js
```

Tool Use

Invoke via babysitter process:

methodologies/superpowers/systematic-debugging