Invoke the rubber duck reviewer for a second opinion. Use after planning, after complex multi-file implementations, or after writing tests. Produces a focused CRITICAL/WARN/INFO list and a APPROVE/REQUEST_CHANGES verdict.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Invoke @rubber-duck to get an independent second opinion on a plan, implementation, or test suite. This is the same pattern as GitHub Copilot CLI's built-in Rubber Duck feature — a different perspective to catch what the primary agent missed.
| Checkpoint | What to pass | What you get back |
|---|---|---|
| After Phase 3 (plan complete) | plan.md + test-plan.md | PLAN REVIEW |
| After complex multi-file implementation | Changed files / diff | CODE REVIEW |
| After tests written, before running | Test files | TEST REVIEW |
| Any time you feel uncertain | Anything relevant | Focused critique |
@rubber-duck Mode: PLAN REVIEW
Plan: <paste plan.md content or path>
Story: <paste story frontmatter + scenarios>
@rubber-duck Mode: CODE REVIEW
Files changed:
- src/scheduler.ts
- src/jobs/notify.ts
- src/queue/index.ts
<paste diff or file content>
@rubber-duck Mode: TEST REVIEW
Test files:
- tests/unit/scheduler.test.ts
- tests/e2e/notify.spec.ts
- features/scheduler.feature
<paste test content>
| Verdict | Orchestrator action |
|---|---|
| APPROVE | Proceed to next phase |
| REQUEST_CHANGES | Send findings to the responsible agent for revision; re-review once |
CRITICAL findings always block. WARN findings are surfaced to the human for a decision. INFO findings are logged but do not block.
/experimental Rubber Duck activates automatically at the same checkpoints. This skill adds equivalent coverage when using Claude Code or OpenCode.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Run WCAG 2.2 Level AA accessibility audits against generated UI. Use when a story has ui:true or when asked to audit accessibility.
The English summary is being prepared. Showing the original description.
Generate a complete component file tree wired to design tokens with tests and Gherkin spec. Use when scaffolding a new UI component.
The English summary is being prepared. Showing the original description.
Extract Gherkin scenarios from story markdown files into runnable .feature files and generate step definition stubs. Use when syncing stories to test suites.
The English summary is being prepared. Showing the original description.
Read and write design tokens in W3C DTCG format (tokens.json) and emit CSS, Tailwind, and Mantine outputs. Use when modifying or generating design tokens.
The English summary is being prepared. Showing the original description.
Apply Docker and Docker Compose best practices for containerising services. Use when writing or reviewing Dockerfiles and compose configs.
The English summary is being prepared. Showing the original description.
Identify and annotate cloud cost implications of architectural decisions. Use when reviewing infrastructure changes or designing new services.
The English summary is being prepared. Showing the original description.