code-review-and-quality

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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 well-structured, highly actionable instruction skill with a clear multi-step workflow and concrete gates. Its main weaknesses are verbosity with cross-section repetition and a monolithic body whose external references are broken.

Suggestions

Extract the stable review checklist, Common Rationalizations table, and Red Flags list into a referenced file under references/ and create the missing security-checklist.md / performance-checklist.md so the inline references resolve.

Tighten or merge the overlapping file-size, rationalization, and honesty guidance across Change Sizing, Red Flags, and Honesty in Review to cut repetition and reduce length.

Replace the bare skill-name mentions ("see security-and-hardening", "see performance-optimization") with explicit relative paths so navigation is one level deep and clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is high-signal and avoids explaining concepts Claude already knows, but at ~397 lines it repeats ideas across sections (file-size thresholds in Change Sizing, Red Flags, and the Checklist; rationalizations and honesty guidance overlap), so it could be tightened.	3 / 5
Actionability	Provides fully executable instruction-skill guidance: a severity-prefix table with author actions, numeric change-size thresholds, a named structural-remedies list, a dependency-review checklist, a multi-model pattern with an example prompt, and a copy-paste review checklist covering the common cases.	5 / 5
Workflow Clarity	The Review Process is a clear five-step sequence (Understand Context, Review Tests, Review Implementation, Categorize Findings, Verify the Verification) with explicit severity labeling and "lead with what matters" as ordering checkpoints; verification is a dedicated step.	5 / 5
Progressive Disclosure	It has good section structure, but the file is monolithic with no bundle files (references/scripts/assets absent) and the only file references — ../../references/security-checklist.md, ../../references/performance-checklist.md, and the security-and-hardening/performance-optimization skills — are dangling (none exist on disk), while reference-like bulk content (the full checklist, rationalizations table, red flags) is all inlined.	3 / 5
	Total	16 / 20 Passed

Description

83%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.

The description is strong: third-person voice, concrete capabilities, and multiple explicit trigger clauses answering both what and when. Minor gaps in synonym coverage keep trigger quality and specificity at 4 rather than 5.

Suggestions

Add natural synonyms like "code review", "PR", or "pull request" to the trigger clause so it matches how users phrase the request.

Briefly enumerate the review axes (correctness, readability, architecture, security, performance) in the description to lift specificity to comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "multi-axis code review", "reviewing code written by yourself, another agent, or a human", "assess code quality across multiple dimensions" — with only minor coverage gaps (the axes themselves are not enumerated here).	4 / 5
Completeness	Clearly states the "what" (multi-axis code review) and gives multiple explicit "Use when..." trigger clauses ("Use before merging any change", "Use when reviewing code...", "Use when you need to assess code quality...").	5 / 5
Trigger Term Quality	Natural phrases a user would say are present ("reviewing code", "merging any change", "assess code quality", "before it enters the main branch"), but common synonyms like "code review", "PR", or "pull request" are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear code-review/quality-gate niche, with only minor overlap risk against the related security and performance skills it references.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: addyosmani/agent-skills
Path: skills/code-review-and-quality/SKILL.md
Commit: df1edb2

Reviewed: about 19 hours 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.