What problem does it solve? Reviewing code changes and documents consistently is hard: reviewers miss edge cases, skip verification checks, or apply inconsistent standards. This Skill runs structured review passes — adversarial critique, edge-case hunting, verification-gap analysis, and editorial structure/prose review — and returns findings in one canonical format. ## Core Features & Use Cases - Multi-lens review: Runs adversarial, edge-case, verification-gap, structure, and prose lenses, each with its own method and stance, selectable per run. - Canonical findings output: Every finding carries location, trigger condition, concrete fix, and potential consequence, emitted as JSON, markdown, or both. - Customizable workflow: A customize.toml file plus team/user override files control lenses, style guides, review guidance, output format, and report destination. - Use Case: Ask for a review of an open pull request; the Skill stages the diff, runs the applicable lenses (in parallel subagents when available), and delivers a triaged findings report grouped by lens. ## Quick Start Ask the assistant to review the current branch diff or a specific file, for example: review the uncommitted changes in this repository.
