meta-codereview-current-diff

Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCK_WITH_OVERRIDE / PASS_WITH_NOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured overview that defers operational detail to the frontmatter composition and explains only trigger surface and fallback behavior. It is concise and well-organized; the only soft spot is that the body's actionability and workflow steps are described rather than given as a checkpointed procedure, since the executable content is in the composition block.

Suggestions

Add a brief '## How it runs' sequence in the body (read_diff → review_safety/review_tests/review_style → arbitrate) with the arbitrate priority rule restated as a numbered checklist, so the workflow is checkpointed without duplicating the frontmatter prompts.

Surface the primary trigger phrase ('codereview my diff') in the description text itself, not only in the frontmatter, to strengthen trigger-term coverage.

Clarify the failed-reviewer recovery as an explicit validate→fix→retry step (e.g. 'inspect step_outputs → re-run the failed reviewer step → re-arbitrate') to lift workflow clarity to a 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what a code review is or how reviewers work; every sentence ('combinator + arbitrate pattern', the G1.6 contract reference) earns its place.	5 / 5
Actionability	Concrete commands and tokens are present ('git diff --cached HEAD', 'git diff HEAD', 'NO_DIFF', 'PASS_WITH_NOTES: clean'), but the executable review logic itself lives in the frontmatter composition rather than the body, leaving minor gaps for an operator reading only the body.	4 / 5
Workflow Clarity	The sequence (read diff → three parallel reviewers → arbitrate) is clear and the Fallback section gives explicit error-recovery for both NO_DIFF and a failed reviewer step, but the validate/fix/retry loop is framed in prose rather than as an explicit checkpointed checklist.	4 / 5
Progressive Disclosure	A short, well-organized body (~30 lines) with clear Trigger surface and Fallback sections and no need for external references, satisfying the under-50-lines simple-skill exception for progressive disclosure.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states what the skill does and when to use it, with distinct verdict vocabulary that minimizes conflict risk. It is only slightly shy of perfect trigger-term coverage because the most natural trigger phrases sit in the frontmatter rather than the description itself.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Read the current uncommitted diff', 'run three independent reviewers (safety + tests-coverage + style) in parallel', 'arbitrate a single BLOCK / BLOCK_WITH_OVERRIDE / PASS_WITH_NOTES verdict' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (read diff → run reviewers → arbitrate verdict) and when ('Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop').	5 / 5
Trigger Term Quality	Natural when-to-use phrasing is present ('Use before commit', 'multi-perspective second-opinion', 'single-reviewer agent loop'), but the concrete trigger phrases like 'codereview my diff' live in the frontmatter rather than the description, leaving a few common terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — a three-reviewer combinator with specific verdict tokens (BLOCK / BLOCK_WITH_OVERRIDE / PASS_WITH_NOTES) — that is unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/exp/meta-codereview-current-diff/SKILL.md
Commit: 94ac35e

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.