Is the Systematic Debugging skill free?

Yes. The skill itself is free from obra/superpowers. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Systematic Debugging SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Systematic Debugging?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Systematic Debugging with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Systematic Debugging

Stops guess-and-check fixes; enforces hypothesis-driven debugging.

by Jesse Vincent · obra/superpowers

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jun 25, 2026
Environment: Claude Code 2.x
Upstream re-checked: Aug 10, 2026 · 095d194

Root-caused a race condition Claude had previously "fixed" three times with guesses. The hypothesis-test-verify loop stopped the guessing.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Systematic Debugging does

Replaces Claude's default "try a plausible fix" behavior with a disciplined loop: reproduce, hypothesize, instrument, verify. Best on bugs that have survived one failed fix already.

How to install Systematic Debugging

/plugin marketplace add obra/superpowers-marketplace
/plugin install superpowers

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Systematic Debugging

/systematic-debugging Stops guess-and-check fixes; enforces hypothesis-driven debugging.

It also activates on plain-language prompts like these:

This bug survived one fix already, debug it systematically
Reproduce this bug and form a hypothesis before fixing it
Instrument the code and verify the root cause of this crash

Appears in

Skills for Developers

Frequently asked questions

Is the Systematic Debugging skill free?: Yes. The skill itself is free from obra/superpowers. SkillProof publishes the install command and an independent test verdict at no cost.
Does Systematic Debugging work with Claude Code?: We tested it with Claude Code 2.x on Jun 25, 2026. Verdict: Tested · Works. Root-caused a race condition Claude had previously "fixed" three times with guesses. The hypothesis-test-verify loop stopped the guessing.
What is the Systematic Debugging SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Systematic Debugging?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Systematic Debugging with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.