Name: uinaf/review
Rating: 98.8 (1 reviews)
Author: uinaf

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.

1.20x

Quality

100%

Does it follow best practices?

Impact

96%

1.20x

Average score across 4 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

22%

Auth Token Module Review

Criteria

Without context

With context

any type flagged

100%

Unsafe cast flagged

100%

Non-null assertion flagged

100%

Dead code identified

100%

Duplicate logic identified

100%

Catch-all error flagged

100%

Error classification recommended

100%

Narrating comments flagged

100%

Findings tied to impact

100%

Valid verdict

100%

Compact verdict block

62%

100%

21%

Review: Payment Retry Logic Changes

Criteria

Without context

With context

CLAUDE.md loaded

100%

File references in findings

100%

Line-level evidence

100%

Verdict present

62%

100%

Findings by severity

100%

Error classification finding

100%

Silent failure finding

75%

100%

Mock-heavy test concern

33%

100%

Dead code identified

100%

Unverified surfaces marked

12%

100%

Recommended follow-up

100%

No nit inflation

83%

100%

Personas listed

87%

100%

Compact verdict block

50%

100%

94%

14%

Code Review: Authentication Middleware Refactor

Criteria

Without context

With context

Default personas used

75%

87%

Types persona included

70%

100%

Cleanup persona included

75%

100%

Comments persona omitted

100%

Repo guidance loaded

100%

Personas listed in output

100%

83%

Verdict present

37%

100%

Scope stated

83%

Findings ordered by severity

100%

Evidence for findings

100%

Silent failures finding

100%

Unverified areas acknowledged

100%

Recommended follow-up

100%

Compact verdict block

66%

50%

91%

Quick Review: Documentation Typo Fix

Criteria

Without context

With context

Minimal personas selected

91%

83%

General persona used

87%

Comments persona used

90%

Tests persona omitted

100%

Verdict present

60%

100%

Scope stated

87%

Personas listed in output

87%

No nit inflation

100%

Docstring accuracy noted

100%

Unverified areas or residual risk

100%

Recommended follow-up

20%

100%

Compact verdict block

87%

62%

Evaluated: 2 days ago
Agent: Claude
Model: Claude Sonnet 4.6

Table of Contents

Auth Token Module Review Review: Payment Retry Logic Changes Code Review: Authentication Middleware Refactor Quick Review: Documentation Typo Fix