uinaf/cross-harness-review
Run a read-only code review through the opposite AI coding harness and return uinaf review-style findings, evidence, unverified gaps, and a ship-it / needs-review / blocked verdict. Use for /review-with-claudex, cross-harness review, opposite-model review, Claude reviewing Codex work, or Codex reviewing Claude work.
97
97%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 a strong skill description that clearly defines a specific niche (cross-harness AI code review), lists concrete outputs (findings, evidence, gaps, verdict), provides multiple natural trigger terms, and explicitly disambiguates from related skills. The only minor issue is the apparent typo 'uinaf' (likely 'unified') which could cause confusion but doesn't significantly impact skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: run a read-only code review, return findings, evidence, unverified gaps, and a ship-it/needs-review/blocked verdict. Also explicitly states what it is NOT (not an implementation or fix loop). | 3 / 3 |
Completeness | Clearly answers both 'what' (run a read-only code review through the opposite AI coding harness and return review-style findings with a verdict) and 'when' (Use for /review-with-claudex, cross-harness review, opposite-model review, etc.). Explicit trigger guidance is present. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: '/review-with-claudex', 'cross-harness review', 'opposite-model review', 'Claude reviewing Codex work', 'Codex reviewing Claude work'. These cover multiple natural phrasings a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: cross-harness AI code review between Claude and Codex. The specific triggers like '/review-with-claudex' and 'opposite-model review' are very unlikely to conflict with generic code review or implementation skills. The explicit 'Not an implementation or fix loop' further disambiguates. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that provides clear, actionable guidance for cross-harness code review. It excels in conciseness and actionability with executable commands, concrete output templates, and a well-defined workflow with validation checkpoints. The only weakness is the reference to a bundle file (references/headless-modes.md) that isn't provided, making it impossible to verify the progressive disclosure chain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It assumes Claude understands concepts like diffs, branches, PRs, and CLI tools. Every section serves a clear purpose with no unnecessary explanation of what code review is or how harnesses work. | 3 / 3 |
Actionability | Provides fully executable CLI commands for both directions (Codex→Claude and Claude→Codex), specific flags and allowed tools, a copy-paste shared prompt template, and concrete output examples for both success and failure cases. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (define target → detect harness → preflight → delegate → preserve findings → stop). It includes explicit preflight validation checks, a blocked verdict path for when the opposite harness is unavailable, and a clear constraint to stop after one review unless explicitly asked for iteration. | 3 / 3 |
Progressive Disclosure | References headless-modes.md for CLI flag details and fallback commands, which is good progressive disclosure. However, the bundle has no files provided, so we cannot verify the reference exists. The main content is well-structured with clear sections but the reference to a non-provided bundle file is a minor concern. | 2 / 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