systematic-debugging
Four-phase root-cause analysis
Install systematic-debugging
npx skills add obra/superpowers --skill systematic-debugging Skills install into ~/.claude/skills/ and load on demand. Other SKILL.md tools (Cursor, Codex, Gemini CLI) use the same files.
What it does
A disciplined reproduce → isolate → identify → verify loop for tracking down hard bugs instead of guessing. Core obra/superpowers skill for production issues and multi-component failures.
- production bugs
- incident triage
Trust & safety
Score 90/100 · High trust- From the widely-used obra/superpowers collection.
- Manually reviewed and verified by Loadout.
- No network access — runs locally only.
- Markdown-only instructions, no bundled scripts.
Heuristic signal based on provenance and capabilities — not a security audit. Always review a skill’s SKILL.md and scripts before first run.
Scan any SKILL.md yourself →Works with
- Claude Code
- Claude.ai
- Claude API
- Cursor
- Codex CLI
- Gemini CLI
Pairs well with these MCP servers
Skills bring the know-how; MCP servers bring the connections.
Related skills
FAQ — systematic-debugging skill
What does the systematic-debugging skill do?
A disciplined reproduce → isolate → identify → verify loop for tracking down hard bugs instead of guessing. Core obra/superpowers skill for production issues and multi-component failures.
How do I install the systematic-debugging skill?
Run: npx skills add obra/superpowers --skill systematic-debugging. Or git clone the repo into ~/.claude/skills/. Skills load automatically when relevant — no extra config.
Which agents support systematic-debugging?
It reads the SKILL.md standard, so it works with Claude Code, Claude.ai, Claude API, Cursor, Codex CLI, Gemini CLI.
Is the systematic-debugging skill safe to run?
High trust (trust score 90/100). From the widely-used obra/superpowers collection. Manually reviewed and verified by Loadout. No network access — runs locally only. Markdown-only instructions, no bundled scripts.