Ralph review
Critically review a current or completed Ralph sprint for specification alignment, implementation correctness, validation evidence, orchestration reliability, and remaining gaps. Use when the user asks to review, audit, accept, or assess a Ralph sprint. Do not implement fixes unless the user separately authorizes them.From its SKILL.md
npx -y skills add zacharygcook/agent-skills --skill ralph-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, 230 tokens by cl100k_base, as published. Nobody here has run it
Ralph Review
Review the sprint as an evidence-backed delivery unit.
- Read repository instructions, the durable spec, sprint
README.md,IMPLEMENTATION_PLAN.md,relevant-specs.md,chunks.json, andSCRATCHPAD.md. - Inspect the actual commit range and changed artifacts. Do not accept summaries as proof.
- Verify every passed chunk against its acceptance criteria, validation logs, and commit evidence.
- Check final review, documentation, sprint-validation, and optional E2E hook states. Distinguish skipped, failed, interrupted, and completed hooks.
- Look for missing spec behavior, accidental scope, weak tests, stale documentation, unsafe orchestration state, and negative knowledge the next sprint must preserve.
- Report findings by severity, then give a clear verdict: complete, repairable before acceptance, or blocked. Name the exact evidence and next action.
Do not rewrite chunk state, manufacture evidence, or implement findings during a review-only request.
When installed beside $ralph-loop, consult references/review.md for the full shared rubric.
What ships with it: 2 files
246 B alongside SKILL.md
agents/
- openai.yaml240 B
assets/
- VERSION6 B