Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, token-efficient skill body: lean prose, executable guidance, a clearly sequenced review workflow with validation checkpoints, and clean one-level progressive disclosure to verified reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean throughout; it assumes Claude's competence, does not re-explain review fundamentals, and every section (scopes table, command cues, severity rubric, output template) earns its place. | 3 / 3 |
Actionability | Provides concrete executable command cues (gh pr view/diff, git diff/show variants), a copy-paste-ready delegate prompt template, and a complete output template rather than vague direction. | 3 / 3 |
Workflow Clarity | Multi-step flow is clearly sequenced (Setup -> Safety -> Coverage -> Flow -> Verification -> Findings Bar -> Output) with explicit verification/validation checkpoints ('verify each retained finding against the diff and nearby code', partial-coverage rules). | 3 / 3 |
Progressive Disclosure | SKILL.md is an overview with clearly signaled one-level-deep references to five existing files (behavior.md, contract.md, test.md, simplicity.md, documentation.md), each verified present in references/; no nested references. | 3 / 3 |
Total | 12 / 12 Passed |