Spawning Reviewers

Stage contract

• Stage: 5a. Review (inside the build loop) · Kind: method
• Inputs: a settled artifact to critique (frozen — no edits while the review runs).
• Outputs: ranked findings anchored to precise locations — no verdict.
• Entry gate: called each review-and-fix iteration by the converging-and-polishing skill.
• Done when: located findings returned from a cross-family / independent critic (unanchored claims don't count).
• Next: back to the converging-and-polishing skill — you fix the real findings, verify, re-spawn.

Overview

A review's value is decided before the reviewer starts working — by how you framed the prompt, which reviewers you picked, and whether you forced them to examine the real thing. Get those wrong and even a strong model returns confident noise.

Core principle: a reviewer is an instrument you can bias or starve without noticing. Tell it what you expect — or even where to look — and it confirms your priors. Don't make it look at the artifact and it reviews your description of the artifact. Pick reviewers that share a brain and their agreement means nothing. This skill is the discipline that prevents all three.

When to use