Is the Debugger skill free?

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

What is the Debugger SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Debugger?

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 Debugger 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.

Debugger

Bug-triage persona: ranked root-cause hypotheses with confirm-steps, minimal fix, regression note

by antonbabenko · antonbabenko/deliberation

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 18, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · 169792a

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 18, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Fed it a Python running_average() that crashed with ZeroDivisionError (total/i, i starting at 0). A plain baseline pass returned the correct one-line fix; following the skill produced the same fix (total/(i+1), verified live to output [10.0,15.0,20.0]) but added the pieces baseline skipped: a confidence-ranked hypothesis, an explicit confirm-step, and a regression note explaining that (i+1) equals the count of elements summed so far so later terms stay correct. The extracted skill is fully self-contained (no scripts, no external refs) and installs cleanly. Docs are honest to the point of under-selling, with a When-NOT-to-Invoke section that tells you to skip obvious bugs.

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 7/10
Docs & honesty 5/5

What Debugger does

A debugging-specialist persona that turns a bug report plus code/logs into confidence-ranked root-cause hypotheses, each with supporting evidence, a quick confirm-step, the smallest safe fix, and a regression note. Includes an honesty escape that reports 'no bug found' instead of inventing one. Triggers on runtime errors, crashes, test failures, wrong output, or after repeated failed fix attempts.

How to install Debugger

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Debugger

/debugger Bug-triage persona: ranked root-cause hypotheses with confirm-steps, minimal fix, regression note

It also activates on plain-language prompts like these:

My test keeps failing with a null pointer, help me find the cause.
I've tried fixing this crash twice already, give me fresh hypotheses.
Why is my function returning the wrong output for these inputs?

Frequently asked questions

Is the Debugger skill free?: Yes. The skill itself is free from antonbabenko/deliberation. SkillProof publishes the install command and an independent test verdict at no cost.
Does Debugger work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 18, 2026. Verdict: Tested · Works. Fed it a Python running_average() that crashed with ZeroDivisionError (total/i, i starting at 0). A plain baseline pass returned the correct one-line fix; following the skill produced the same fix (total/(i+1), verified live to output [10.0,15.0,20.0]) but added the pieces baseline skipped: a confidence-ranked hypothesis, an explicit confirm-step, and a regression note explaining that (i+1) equals the count of elements summed so far so later terms stay correct. The extracted skill is fully self-contained (no scripts, no external refs) and installs cleanly. Docs are honest to the point of under-selling, with a When-NOT-to-Invoke section that tells you to skip obvious bugs.
What is the Debugger SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Debugger?: 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 Debugger 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.