code-reviewer

Elite code review expert specializing in modern AI-powered code

Quality

30%

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 ./skills/code-reviewer/SKILL.md

Quality

Content

31%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 body is a verbose capability catalog that enumerates tools and concepts Claude largely already knows, with almost no executable guidance and a broken reference to a missing playbook file. Its only structural workflow is a high-level 10-step list without validation checkpoints.

Suggestions

Cut the generic knowledge catalogs (OWASP Top 10, N+1, SOLID, tool name lists) and keep only tool-specific configuration or rules Claude would not already know.

Replace the abstract Instructions with concrete, executable steps, e.g. specific commands to run Semgrep/Semgrep/Bandit or a copy-paste review checklist.

Either create the referenced resources/implementation-playbook.md or remove the broken reference, and move the large capability lists into one-level-deep reference files with clearly signaled links.

Dimension	Reasoning	Score
Conciseness	The body is a large catalog of capability bullet lists (AI tools, static analysis, OWASP, N+1, SOLID) much of which Claude already knows, plus fluffy sections like 'Expert Purpose', 'Behavioral Traits', and 'Knowledge Base'; this is noticeably verbose with several padded sections rather than the mostly-efficient score-3 anchor.	2 / 5
Actionability	The Instructions are abstract ('Clarify goals', 'Apply relevant best practices and validate outcomes') and the Response Approach is high-level with no commands or code; the only concrete pointer ('open resources/implementation-playbook.md') targets a file that does not exist, fitting the minimal-concrete-guidance anchor rather than the score-3 pseudocode anchor.	2 / 5
Workflow Clarity	The 10-step 'Response Approach' gives a recognizable sequence for conducting a review, but there are no validation checkpoints or error-recovery loops and steps are high-level; this matches the steps-listed-but-checkpoints-missing anchor. No destructive/batch cap applies since review is analytical, not destructive.	3 / 5
Progressive Disclosure	The skill is a monolithic file with capability catalogs that clearly belong in separate reference files, and its single external reference (resources/implementation-playbook.md) is broken because no such file exists; this fits the minimal-structure/inlined-content anchor better than the score-3 some-structure anchor.	2 / 5
	Total	9 / 20 Passed

Description

28%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 a brief, role-based tagline rather than a capability-and-trigger statement: it names code review as the domain but lists no concrete actions and provides no 'Use when' guidance. It is too vague to reliably route users to this skill.

Suggestions

Replace the role title with concrete actions, e.g. 'Reviews code for bugs, security vulnerabilities, performance issues, and maintainability using static analysis and AI-assisted tools.'

Add an explicit trigger clause, e.g. 'Use when reviewing a pull request, auditing code for security/performance issues, or setting up code review automation.'

Drop the marketing language ('Elite', 'modern AI-powered') which adds no routing signal.

Dimension	Reasoning	Score
Specificity	The description names the domain ('code review') but offers no concrete actions, only a role title ('Elite code review expert specializing in modern AI-powered code'). It matches the anchor that names the domain with minimal/generic actions rather than the score-3 anchor requiring 1-2 concrete actions.	2 / 5
Completeness	The description provides a vague 'what' (a role, not actions) and no 'when'/'Use when' clause at all, matching the vague-what-and-no-when anchor; the score-3 anchor requires a clear 'what', which a role title does not provide.	2 / 5
Trigger Term Quality	'code review' is a natural user phrase, but it is the only real trigger term alongside the buzzword 'AI-powered code'; common variations like 'review my code', 'PR review', or 'pull request review' are missing, fitting the one-or-two-generic-keywords anchor rather than the score-3 partial-coverage anchor.	2 / 5
Distinctiveness Conflict Risk	'code review' is a recognizable niche, but the phrasing is broad and role-based, so it could still overlap with general coding or security-review skills; this fits the somewhat-specific-but-could-overlap anchor better than the mostly-distinct score-4 anchor.	3 / 5
	Total	9 / 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: sickn33/agentic-awesome-skills
Path: skills/code-reviewer/SKILL.md
Commit: b1aebac

Reviewed: ~17 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.