Frontend Design
Use Claude Code to create production-ready interfaces that look professional, not AI-generated. React, Tailwind, and clean design automatically.
Forces root-cause investigation across four phases before any fix when tests fail or behavior looks wrong.
Creator, superpowers
Forces root-cause investigation across four phases before any fix when tests fail or behavior looks wrong.
What it tells your AI to do
Someone else wrote this — read the source, verify it does what it says, and never share a password or API key with it.
Debug this failure using systematic debugging. Complete root-cause investigation before proposing any fix; show reproduction steps and evidence.
A skill is instructions your AI follows. Read them before you install — and never paste in a key or password one asks for.
# Systematic Debugging Iron law: no fixes without root-cause investigation first. ## When to use Test failures, production bugs, unexpected behavior, performance issues, build or integration failures — especially under time pressure. ## Four phases 1. Root cause investigation — read errors fully, reproduce, gather evidence, form a hypothesis. 2. Pattern analysis — compare working vs broken paths; find the smallest failing case. 3. Hypothesis and test — change one variable; confirm the cause. 4. Implementation — fix the cause, add regression coverage, verify. Skip no phase. Symptom patches that leave the cause intact are failures. Adapted from @obra's approach: https://github.com/obra/superpowers/tree/main/skills/systematic-debugging
No comments yet — be the first.
Use Claude Code to create production-ready interfaces that look professional, not AI-generated. React, Tailwind, and clean design automatically.
Use Claude Code to test web applications and find bugs before users do. Automated browser testing with plain English commands.
Use Claude Code to build MCP servers that connect Claude to your APIs, databases, and tools. Working server with auth and error handling in minutes.