code-review

Thorough code review of branch changes. Supports automatic/interactive fixing, instruction-based, agnostic, or combined review lenses. Use when: review my code, review this branch, do a code review, review branch changes, check my changes. Input: [--base <branch>] [--mode automatic|interactive] [--lens instructions|agnostic|both]

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%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 highly actionable, well-sequenced review workflow with concrete commands, templates, and validation feedback loops. Its main weakness is conciseness: a duplicated 'Important Rules' section and some motivational prose inflate the body.

Suggestions

Remove or fold the 'Important Rules' section into the workflow steps — bullets like 'Problem first, then conventions', 'Trace, don't trust', and 'State preconditions for every shortcut' already duplicate Step 4 content.

Trim motivational asides ('skipping it is the most common way a review misses a bug', 'Doc-comment drift is one of the most common refactor regressions') that persuade rather than instruct.

Consider extracting the detailed Step 4 semantic-pass methodology or the large-diff scaling guidance into a reference file to shorten the core SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable methodology, but the 'Important Rules' section largely restates Step 4 principles and motivational prose ('skipping it is the most common way a review misses a bug') could be trimmed.	3 / 5
Actionability	Copy-paste-ready git diff commands, npm quality-tool commands, a concrete issue-table template with an example row, and explicit file-exclusion lists give fully executable guidance.	5 / 5
Workflow Clarity	A clear 9-step sequence with explicit validation checkpoints (Step 6 baseline, Step 8 re-run after fixes) and fix→re-verify feedback loops; the destructive auto-fix cap does not apply because validation is present.	5 / 5
Progressive Disclosure	Well-organized into clear sections with a clearly signaled external reference (instructions/index.md); no bundle files exist, but the cohesive workflow content is appropriately placed with only minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

91%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 clearly states the skill's purpose and gives concrete, natural-language trigger phrases. It is specific and complete, with only minor room to enumerate the review's concrete checks and sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Thorough code review', 'automatic/interactive fixing', and three review lenses — with only minor gaps in coverage of what the review actually checks.	4 / 5
Completeness	Explicitly answers both what it does (review + fixing + lenses) and when to use it via a concrete 'Use when' trigger clause, matching the anchor-5 example pattern.	5 / 5
Trigger Term Quality	'review my code, review this branch, do a code review, review branch changes, check my changes' provides comprehensive natural phrasings with synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	'Code review of branch changes' is a clear niche with distinct triggers, with only minor overlap risk against closely related dev-workflow skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: BabylonJS/Babylon.js
Path: .github/skills/code-review/SKILL.md
Commit: 787eedf

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.