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

63%

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

56%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.

The skill body is reasonably concise and points to two genuinely useful, executable scripts, but its progressive disclosure is undermined by referencing template files (templates/review-checklist.md, templates/finding-template.md) that are absent from the bundle. Workflow clarity is also only implicit — there is no sequenced review process with checkpoints.

Suggestions

Either add the missing templates/ files (review-checklist.md, finding-template.md) or remove the references to them so navigation is not broken.

Add an explicit ordered review workflow (e.g., run analyze-metrics.py → run compare-complexity.py for diffs → categorize findings → report with template) with a validation/checkpoint step.

Tighten the four repeated category bullet lists or move them into the checklist reference to further improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is largely a tight taxonomy of review categories plus concise reference listings and a template outline; it assumes Claude's competence and avoids explaining basic concepts, with only minor padding (e.g., the verbose four-category bullet lists).	4 / 5
Actionability	It provides concrete, executable scripts (analyze-metrics.py, compare-complexity.py with real invocations) but the core review guidance is a descriptive checklist/template rather than specific executable steps or code examples for the review act itself.	3 / 5
Workflow Clarity	A review process is implied via the template and reference-file instructions, but there is no explicit sequenced workflow with validation checkpoints; the destructive/batch cap (analyzing code is non-destructive) does not apply, yet checkpoints are still missing or only implicit.	3 / 5
Progressive Disclosure	The body references two template files (review-checklist.md, finding-template.md) under a templates/ path that do not exist in the bundle (only scripts/ is present), so the signaled navigation points to missing files; the two real scripts are referenced clearly, but the broken template references sink organization.	2 / 5
	Total	12 / 20 Passed

Description

71%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 well-structured with a clear 'Use when' clause and good natural trigger terms, making it genuinely actionable for routing. Its main weakness is breadth — 'security, performance, and quality analysis' is a wide niche with moderate overlap risk against general coding skills.

Suggestions

Narrow the 'what' to more specific concrete actions (e.g., 'Identifies security vulnerabilities, flags performance regressions, and grades code quality') to reduce overlap with general coding skills.

Add negative boundary guidance to the trigger clause (e.g., 'Do not use for simple linting or formatting') to lower conflict risk with adjacent skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('security, performance, and quality analysis') and several concrete actions ('review code', 'analyze code quality', 'evaluate pull requests'), though coverage is broad rather than a tight enumeration of specific concrete actions.	4 / 5
Completeness	Clearly states what it does and provides an explicit 'Use when users ask to review code, analyze code quality, evaluate pull requests, or mention...' trigger clause; the 'when' could be slightly more explicit about excluded cases but both halves are present.	4 / 5
Trigger Term Quality	Includes natural user phrases ('review code', 'analyze code quality', 'evaluate pull requests', 'security analysis', 'performance optimization'); a few common synonyms are missing but coverage is good.	4 / 5
Distinctiveness Conflict Risk	Code review is a fairly broad niche that overlaps with general coding skills and built-in review capabilities; the triggers are reasonably distinct but not a sharp low-conflict niche.	3 / 5
	Total	15 / 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: luongnv89/claude-howto
Path: 03-skills/code-review-specialist/SKILL.md
Commit: 1c04dbf

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.