uinaf/review
Review existing code, diffs, branches, or pull requests using concern-specific reviewer personas and evidence. Use when auditing someone else's work, triaging risk in a PR, or producing a ship-it / needs-review / blocked verdict. Do not use to verify your own completed change; use `verify` for that.
98
100%
Does it follow best practices?
Impact
96%
1.20xAverage score across 4 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates what the skill does (independent code auditing with reviewer personas producing a verdict), when to use it (PR triage, ship decisions, post-verify follow-up), and when NOT to use it (self-checking authored changes). The description is concise, uses third-person voice, includes natural trigger terms, and explicitly disambiguates from a related skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: audit code/diffs/branches/PRs, use concern-specific reviewer personas, produce a ship-it/needs-review/blocked verdict. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('audit existing code, diffs, branches, or pull requests using concern-specific reviewer personas') and when ('triaging risk in a PR, deciding whether a change is safe to ship, or following up on a verify pass'). Also includes explicit anti-triggers ('Do not use to self-check a change you just authored'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'audit', 'PR', 'pull requests', 'diffs', 'branches', 'risk', 'safe to ship', 'review', 'code review'. Also includes the contrast with 'verify' which helps disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: independent code review with verdict output. Explicitly differentiates itself from the 'verify' skill, reducing conflict risk. The reviewer-persona approach and verdict output format are unique identifiers. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently communicates a complex multi-persona code review workflow. It excels at actionability with concrete commands, specific file references, and a detailed output format with examples. The progressive disclosure is well-structured with clear navigation to specialized reviewer personas and reference materials.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient throughout. It assumes Claude's competence, avoids explaining basic concepts, and every section earns its place. The output format rules are detailed but necessary for consistent behavior. No padding or unnecessary context. | 3 / 3 |
Actionability | Provides concrete git commands, specific persona file references, explicit verdict labels, a structured output format with an example, and clear decision criteria (e.g., persona shortcuts for doc-only diffs, mock-heavy tests). The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | The four-step workflow (scope → run personas → collect evidence → synthesize verdict) is clearly sequenced with explicit validation checkpoints (cite exact file references, run smallest runtime check, explicitly state unverified items). The 'Before You Start' section adds a pre-flight checklist. Error handling is addressed through the evidence collection step's requirement to flag unverified claims. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to reviewer personas (reviewers/*.md) and reference docs (references/*.md). The persona shortcuts section helps users navigate which references to load without requiring them to read everything upfront. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents