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
92%
1.31xAverage score across 3 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 communicates what the skill does, when to use it, and importantly when NOT to use it. It uses concrete terminology that maps well to natural user requests, includes multiple trigger terms, and explicitly differentiates itself from a related skill ('verify'). The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Review existing code, diffs, branches, or pull requests', 'using concern-specific reviewer personas and evidence', 'producing a ship-it / needs-review / blocked verdict'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Review existing code, diffs, branches, or pull requests using concern-specific reviewer personas and evidence') and when ('Use when auditing someone else's work, triaging risk in a PR, or producing a verdict'). Also includes explicit negative boundary ('Do not use to verify your own completed change'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'code review', 'diffs', 'branches', 'pull requests', 'PR', 'auditing', 'risk', 'ship-it', 'blocked verdict'. Good coverage of common variations including 'PR' shorthand. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (reviewing others' code, not your own). The explicit negative boundary distinguishing it from 'verify' skill reduces conflict risk. The specific triggers like 'PR', 'auditing', 'reviewer personas', and verdict types create a clear identity. | 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 structured code review process. It excels at progressive disclosure with well-organized references to specialized reviewer personas, provides concrete commands and output examples, and maintains a clear workflow with evidence-based validation checkpoints. The handoff section cleanly delineates when to use this skill versus related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose—no unnecessary explanations of what code review is or how git works. Principles are terse, handoffs are clear, and the workflow avoids padding. | 3 / 3 |
Actionability | Provides concrete git commands (`git diff --stat`, `git diff <base>...HEAD -- <path>`, `pnpm test path/to/spec`), specific verdict categories, a structured output template with a realistic example, and explicit file references to reviewer personas. 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: citing exact file references, running runtime checks, and explicitly flagging unverified areas rather than bluffing. The feedback loop of evidence-based verification before verdict is well-articulated. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure: the SKILL.md provides a clear overview and workflow, then links to one-level-deep references for reviewer personas, reviewer selection guidance, and detailed reviewing methodology. Default vs conditional personas are clearly separated with direct file links. | 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