What problem does it solve? Reviews of code changes and documents are often shallow or inconsistent, missing edge cases, untested behavior, and structural writing problems. This Skill runs a structured multi-lens review over any diff, spec, or document and reports concrete findings in a canonical format. ## Core Features & Use Cases - Multi-lens review: Run adversarial, edge-case, verification-gap, structure, and prose lenses singly or together, with each lens applying its own method and findings shape. - Configurable workflow: Customize lenses, style guides, reader type, output format, and standing review directives through TOML overrides without editing the shipped skill. - Grounded editorial review: Compute exact per-section word counts with the bundled word_metrics.py script so structural recommendations cite real reduction numbers. - Use Case: After opening a pull request, ask for a critical review of the diff; the edge-case hunter enumerates unhandled branches, the verification-gap lens checks whether tests would catch a regression, and findings arrive as JSON plus a markdown report. ## Quick Start Ask the AI to review the current diff or a document, for example: run a critical review of my uncommitted changes and report edge cases and verification gaps.
