code-review-specialist

Comprehensive code review with security, performance, and quality analysis. Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./03-skills/code-review-specialist/SKILL.md

Quality

Content

37%

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

The body organizes review categories and provides a usable output template, but it enumerates concepts Claude already knows, lacks a sequenced review workflow with validation, and points to two template files that are missing from the bundle.

Suggestions

Add a numbered review workflow that sequences the existing scripts (e.g., 1. run scripts/analyze-metrics.py, 2. work through security/performance/quality categories, 3. cross-check against the checklist, 4. report via the finding template) with a validation checkpoint before finalizing findings.

Either create the missing templates/review-checklist.md and templates/finding-template.md or remove the references to them so navigation is not broken.

Trim the concept-enumeration bullets (SOLID principles, Big O analysis, design patterns, naming conventions, etc.) to the few non-obvious heuristics Claude would not already apply, keeping the body lean.

Dimension	Reasoning	Score
Conciseness	The body is structured rather than prose-padded, but the category sub-bullets enumerate concepts Claude already knows ("SOLID principles", "Big O analysis", "injection vulnerabilities", "Design patterns", "Type safety"), which could be trimmed.	2 / 3
Actionability	The output template (Summary / Critical Issues / Findings by Category) is concrete, and the two scripts exist, but two of the four referenced files (templates/review-checklist.md, templates/finding-template.md) do not exist, leaving key guidance incomplete.	2 / 3
Workflow Clarity	There is no sequenced review process — the body is a category taxonomy plus an output format, with no ordered steps (e.g., run metrics, inspect security, validate findings) or checkpoints tying the scripts to the review flow.	1 / 3
Progressive Disclosure	References are well-signaled with bold names and when-to-read guidance and are one level deep, but navigation is broken because templates/review-checklist.md and templates/finding-template.md are referenced yet absent from the bundle.	2 / 3
	Total	7 / 12 Passed

Description

82%

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 description with an explicit 'Use when...' trigger clause and natural keyword coverage; its main weakness is naming activity categories rather than concrete, fine-grained actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several activities ("code review", "security analysis", "performance optimization"), but these are category labels rather than concrete actions like the score-3 anchor's "extract text, fill forms, merge documents".	2 / 3
Completeness	Explicitly answers both what ("Comprehensive code review with security, performance, and quality analysis") and when ("Use when users ask to review code... or mention code review, security analysis, or performance optimization").	3 / 3
Trigger Term Quality	Natural user phrasing is well covered — "review code", "analyze code quality", "evaluate pull requests", "code review", "security analysis", "performance optimization" are all terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Triggers are review-focused and reasonably distinct, but "code review / security analysis / performance optimization" is broad enough to overlap with general coding or general-purpose skills.	2 / 3
	Total	10 / 12 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: luongnv89/claude-howto
Path: 03-skills/code-review-specialist/SKILL.md
Commit: 97fc961

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.