code-reviewer

Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.

Quality

32%

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

10%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 enumeration of capabilities, tools, and traits Claude already knows, with no executable guidance, no concrete review workflow, and no progressive disclosure via bundle files. It reads as a marketing-style capability list rather than actionable skill instructions.

Suggestions

Replace the tool/concept enumerations with a concrete, executable review procedure (e.g., specific commands like 'semgrep --config=p/ci', 'npx eslint', or a checklist of checks to run per file).

Add explicit validation checkpoints to the Response Approach (e.g., 're-run scan after fixes; confirm no new findings before approving') to support batch/destructive review operations.

Move the long capability and knowledge-base lists into a reference file (e.g., references/capabilities.md) and keep SKILL.md as a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The ~167-line body is heavily padded with bullet lists enumerating well-known tools and concepts Claude already knows (SonarQube, CodeQL, OWASP Top 10, cyclomatic complexity, SOLID), adding almost no information Claude does not already have.	1 / 5
Actionability	There is no executable code, no commands, and no concrete review procedure; the content only describes ('Integration with modern AI review tools', 'OWASP Top 10 vulnerability detection') rather than instructing how to actually perform a review.	1 / 5
Workflow Clarity	A 10-step 'Response Approach' gives a rough sequence ('Analyze code context', 'Apply automated tools', 'Conduct manual review'), but steps are high-level with no concrete commands, no validation checkpoints, and no error-recovery loops.	2 / 5
Progressive Disclosure	Although headers provide some structure, the lengthy capability/tool/knowledge enumerations are all inlined in SKILL.md with no bundle files and no one-level-deep references to move detail out of the overview.	2 / 5
	Total	6 / 20 Passed

Description

55%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 clearly communicates the skill's domain and lists several concrete capabilities, but it lacks an explicit 'Use when...' trigger clause and natural user phrases. It is reasonable but not exemplary, scoring in the mid-range across most dimensions.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to review code, find bugs or security issues, or audit a PR/changeset' to raise completeness.

Surface natural user phrases (e.g., 'review my code', 'find vulnerabilities', 'audit this PR') rather than only technical labels like 'static analysis' and 'code quality assurance'.

Tighten distinctiveness by naming the trigger surface (pull requests, diffs, production config) so it does not overlap with general debugging or refactoring skills.

Dimension	Reasoning	Score
Specificity	Names the code-review domain and several concrete actions ('static analysis tools, security scanning, and configuration review', 'security vulnerabilities, performance optimization'), but verbs like 'Masters'/'specializing in' keep it slightly below fully comprehensive coverage.	4 / 5
Completeness	The 'what' is clearly stated (AI-powered analysis, security, performance, reliability), but the 'when' is only weakly implied via 'Use PROACTIVELY for code quality assurance' rather than an explicit trigger clause with concrete conditions.	3 / 5
Trigger Term Quality	'code review', 'code quality assurance', and 'Use PROACTIVELY' offer some relevant keywords, but common natural phrases users would say ('review this code', 'find bugs', 'security review', 'review my PR') are missing.	3 / 5
Distinctiveness Conflict Risk	The code-review niche is somewhat specific, but the broad phrasing ('code analysis', 'best practices') could overlap with general debugging, refactoring, or security-audit skills.	3 / 5
	Total	13 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/code-reviewer/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.