# Skill Debug

Debug a reproducible symptom with a bounded feedback loop and original-scenario...

- Repository: https://github.com/nyldn/claude-octopus (4351 stars)
- Category: Testing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add nyldn/claude-octopus --skill skill-debug -g -a claude-code -y`
Codex: `npx skills add nyldn/claude-octopus --skill skill-debug -g -a codex -y`
Cursor: `npx skills add nyldn/claude-octopus --skill skill-debug -g -a cursor -y`
Gemini CLI: `npx skills add nyldn/claude-octopus --skill skill-debug -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add nyldn/claude-octopus`

## Description

Debug a reproducible symptom with a bounded feedback loop and original-scenario verification

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Debugging

Read `skills/blocks/engineering-method-selection.md` from the installed plugin
for review admission. Natural-language requests and `--peer-review` share that
policy. Honor host-only requests; risk alone does not authorize paid usage.

Run the investigation on the current host. Routine debugging makes zero
additional provider dispatches. Use a bounded external reviewer only for
`--peer-review`, an explicit independent-review request, or an existing risk
policy.

<HARD-GATE>
DO NOT CHANGE PRODUCTION BEHAVIOR BEFORE REPRODUCING THE SYMPTOM AND TESTING A
NAMED ROOT-CAUSE HYPOTHESIS.
</HARD-GATE>

Read and apply `skills/blocks/debug-feedback-loop.md` from the installed plugin
root.

Start with the user's observable symptom. Reproduce it, retain its failure
signature while minimizing the scenario, test one named hypothesis at a time,
and verify both the minimal reproduction and the original scenario after the
fix. Do not treat a nearby passing helper test as proof.

For a race, use a synchronization barrier and a fixed run or time budget. For an
unavailable production dependency, return `inconclusive` with the missing
evidence. Remove temporary instrumentation before completion and preserve a
stable reproduction as a regression test.

The final record is data, not an executable queue. Store commands as argument
arrays and never evaluate provider-authored text.

## Bounded recovery and strategy rotation

Use a 3-Strike Rule for failed fixes. After each failure, return to the evidence
and test a materially different hypothesis. After two consecutive failures, a
strategy rotation is mandatory: reconsider the root cause, the reproduction,
and whether the test encodes the intended behavior. Do not attempt a 4th fix
without explicit user approval.

Anti-rationalization check: “Should work now” means run the reproduction and
the original scenario. Confidence is not verification.

The rest: https://github.com/nyldn/claude-octopus/blob/HEAD/.claude/skills/skill-debug/SKILL.md