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.
94
94%
Does it follow best practices?
Impact
95%
1.18xAverage 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 specific capabilities (auditing code/PRs with reviewer personas, producing verdicts), provides explicit trigger conditions, and proactively distinguishes itself from a related skill ('verify'). The inclusion of both 'Use when' and 'Do not use' clauses makes it exceptionally well-suited for skill selection in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: audit existing code, diffs, branches, or pull requests; uses concern-specific reviewer personas and evidence; produces a ship it / needs review / blocked verdict. These are concrete, well-defined 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 'Do not use' guidance which strengthens the when clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'audit', 'PR', 'pull requests', 'diffs', 'branches', 'safe to ship', 'triaging risk', 'review', 'verdict'. Also distinguishes from 'verify' which helps avoid false triggers. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: independent code review/audit with verdict output. Explicitly differentiates itself from the 'verify' skill with a 'Do not use' clause, which directly reduces conflict risk with the most likely overlapping skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides clear, actionable guidance for code review with concern-specific personas. The workflow is well-sequenced with explicit evidence requirements and verdict synthesis. Minor verbosity in the output formatting rules and principles section prevents a perfect conciseness score, but overall the skill is highly effective and well-organized.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and avoids explaining basic concepts, but some sections are slightly verbose — e.g., the 'Principles' list includes items that could be trimmed, and the output section has extensive formatting rules that border on over-specification. The persona shortcuts section is well-done and lean. | 2 / 3 |
Actionability | Provides concrete git commands, specific file paths, exact verdict labels, a structured output format with an example, and clear persona selection criteria with shortcuts for common diff shapes. The workflow steps give specific starting points rather than vague direction. | 3 / 3 |
Workflow Clarity | The four-step workflow (scope → run personas → collect evidence → synthesize verdict) is clearly sequenced with explicit validation expectations: citing exact file references, running runtime checks when they change the verdict, and explicitly flagging unverified items. The feedback loop of evidence-based verdict synthesis with residual risk tracking is well-defined. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in SKILL.md and well-signaled one-level-deep references to reviewer personas (reviewers/*.md) and reference docs (references/*.md). Content is appropriately split between the main skill and supporting files, with clear navigation links throughout. | 3 / 3 |
Total | 11 / 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