What problem does it solve?
Code and document reviews are inconsistent: reviewers miss edge cases, verification gaps go unnoticed, and editorial feedback varies by reviewer. This Skill runs structured review lenses — adversarial critique, edge-case tracing, verification-gap analysis, structure, and prose — over a diff, pull request, or document and returns findings in one canonical shape.
Core Features & Use Cases
- Multi-lens review: Runs adversarial, edge-case-hunter, verification-gap, structure, and prose lenses, each with its own method and stance, selected automatically by content type or explicitly by the caller.
- Canonical findings output: Every finding carries location, trigger condition, guard snippet, and potential consequence, rendered as JSON, markdown, or both.
- Customizable workflow: Teams and individuals override lenses, style guides, review guidance, and output preferences through TOML override files without editing the shipped configuration.
- Use Case: Ask for a review of an open pull request; the Skill stages the diff, runs the applicable lenses in parallel, and returns a triaged report grouping findings by lens — including unhandled edge cases and tests that would not catch a regression.
Quick Start
Ask the assistant to review the current branch's diff or a specific pull request and report the findings grouped by lens.
