★ Reviewing slop pull requests

A developer at Perrotta.dev describes a two-step workflow for reviewing AI-generated pull requests using two custom skills: /meat, which converts a diff into a reading guide, and /dual-review, which runs two review passes to validate findings. The sequence is recommended for long, plausible PRs to reduce narrative noise and unsupported findings.

♠ Problem statement : review an AI-written ~~slop~~ pull request from a teammate. We’ll use a clanker https://lucumr.pocoo.org/2026/5/26/clankers/ to review slop PRs. First , I invoke the /meat https://github.com/thiagowfx/skills/blob/master/plugins/thiagowfx/skills/meat/SKILL.md skill, turning the diff into a reading guide, inspired by /meat <PR-URL It does not look for defects. It captures the diff once, follows control and data flow, treats tests as specifications, and returns this shape: One sentence with intent and observable result. Read in this order - path:line — why this contract matters Flow 1. input 2. transformation 3. effect Contracts Tests as specs Omitted That gives me the author’s system model the “meat” of their PR without the PR body’s narrative. Second , /dual-review 1 tries to break that model: /dual-review <PR-URL --post It runs two review passes with different lenses / perspectives, then validates every candidate against source and focused probes. Reviewer agreement changes investigation priority. To recap: /meat says what the change means and where to read it. /dual-review checks whether contracts survive hostile input.My default sequence for a long, plausible PR is now: /meat <PR-URL /dual-review <PR-URL --post One tool removes narrative noise. The other removes findings without evidence. Inspired by an internal skill created by our CISO. ↩︎ https://perrotta.dev/2026/08/reviewing-slop-pull-requests/ fnref:1 — § — Reply via email mailto:serendipity@perrotta.dev?subject=Reply to: Reviewing slop pull requests