uinaf/autoreview
Run structured Codex/Claude autoreview closeout: choose the target, collect schema-validated findings, and rerun tests plus review until clean.
80
100%
Does it follow best practices?
Impact
—
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 articulates what the skill does (structured autoreview closeout with specific steps and targets), when to use it (with an explicit 'Use when' clause listing multiple natural trigger terms), and occupies a distinct niche. The description is concise, uses third-person voice, and provides enough detail for Claude to confidently select it from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'choose the target, run the bundled review helper, validate findings, and rerun focused tests until clean.' Also specifies the types of targets: 'uncommitted changes, branch/PR diffs, or single commits.' | 3 / 3 |
Completeness | Clearly answers both 'what' (run structured autoreview closeout for various diff targets, validate findings, rerun tests) and 'when' (explicit 'Use when asked for autoreview, Codex review, Claude review, automated PR review, second-model review, or merge-readiness review'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'autoreview', 'Codex review', 'Claude review', 'automated PR review', 'second-model review', 'merge-readiness review'. These cover multiple natural phrasings a user might employ. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining automated code review with a specific closeout workflow (Codex/Claude autoreview). The trigger terms like 'autoreview', 'second-model review', and 'merge-readiness review' are specific enough to avoid conflicts with general code review or testing skills. | 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 is concise, actionable, and well-structured. It provides executable commands for every scenario, clear workflow sequencing with validation checkpoints and feedback loops, and appropriate progressive disclosure to supporting files. The contract section is particularly strong, establishing precise behavioral boundaries without unnecessary verbosity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what code review is, what diffs are, or how git works. Every section serves a distinct purpose—contract constraints, target selection, parallel execution, and final reporting. The bullet points are terse and assume Claude's competence. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready bash commands for every target mode (local, branch/PR, commit, parallel). Includes practical patterns like resolving the PR base with `gh pr view`, passing optional context files, and resolving the helper path. The contract rules are specific and unambiguous. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: resolve helper → pick target → run review → validate findings → rerun tests/review until clean → produce final report. Explicit validation checkpoints exist (exit 0 with no findings), feedback loops are stated (rerun focused tests and review after code edits), and the contract includes clear stop conditions and error handling (retry on capacity, don't over-review). | 3 / 3 |
Progressive Disclosure | The SKILL.md serves as a clear overview with well-signaled one-level-deep references to `references/troubleshooting.md`, `references/upstream.md`, `scripts/autoreview`, and `scripts/test-review-harness`. Content is appropriately split between the overview and referenced files, and navigation is straightforward. | 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