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

34%

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

18%

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

The skill body reads as a verbose persona/coverage document: long lists of tools and concepts Claude already knows, with no executable examples, no commands, and no real validation-driven workflow. It is sectionally organized but overlong and not actionable.

Suggestions

Cut the tool/concept enumerations (Capabilities, Knowledge Base) down to the few non-obvious specifics and remove topics Claude already knows; aim for a lean overview that points to detail files.

Add concrete, executable guidance: example review commands (e.g. `semgrep --config=p/python`), sample PR-review checklists, or a minimal code example of a finding and its fix.

Turn the 'Response Approach' into a verifiable workflow with explicit validation checkpoints (e.g. 'Run static analysis; only report findings that reproduce; confirm severity before flagging').

Dimension	Reasoning	Score
Conciseness	The ~167-line body is padded with capability/tool/topic enumerations ('SonarQube, CodeQL, and Semgrep', 'OWASP Top 10', 'SOLID pattern adherence') that largely restate knowledge Claude already has; nearly every token is descriptive padding rather than earned instruction.	1 / 3
Actionability	There is no executable code, no concrete commands, and no specific tool invocations; guidance is abstract ('Apply automated tools', 'Conduct manual review', 'Provide structured feedback organized by severity') and describes rather than instructs.	1 / 3
Workflow Clarity	The numbered 'Response Approach' gives a sequenced 10-step process, which is a clear sequence, but it has no validation checkpoints or feedback loops for risky review outcomes, and the steps are high-level directives rather than a verifiable workflow.	2 / 3
Progressive Disclosure	The body is organized into clearly headed sections (Capabilities, Behavioral Traits, Knowledge Base, Response Approach), but it is a single monolithic overview with no external bundle files and no one-level-deep references, so most detail that should be split out is inline.	2 / 3
	Total	6 / 12 Passed

Description

50%

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 conveys a broad code-review/security/performance domain and includes a trigger cue, but it leans on buzzwords ('Elite', 'Masters', '2024/2025 best practices') and lacks concrete, distinctive 'Use when ...' triggers. It is adequate but not sharp.

Suggestions

Replace marketing language ('Elite code review expert', 'Masters ...', '2024/2025 best practices') with concrete actions such as 'Review pull requests, detect security vulnerabilities, and flag performance regressions.'

Add an explicit, situation-based trigger, e.g. 'Use when reviewing staged changes, pull requests, or production code for security, performance, and maintainability issues.'

Narrow the scope to reduce overlap with general security/dev skills, or add distinctive triggers ('review my code', 'audit this PR', 'find bugs').

Dimension	Reasoning	Score
Specificity	Names the code-review domain and several concrete capability areas ('static analysis tools, security scanning, and configuration review', 'security vulnerabilities, performance optimization'), but they are tool/category-level rather than discrete actions, and 'Elite code review expert' and 'Masters ...' add puffery rather than specificity.	2 / 3
Completeness	It states what the skill does across multiple capabilities, and includes a trigger clause ('Use PROACTIVELY for code quality assurance'), but that trigger is generic rather than an explicit 'Use when ...' tied to concrete situations, which caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant terms ('code', 'review', 'security vulnerabilities', 'performance') and an explicit 'Use PROACTIVELY for code quality assurance' are present, but it omits natural phrasings a user would actually say like 'review my code', 'find bugs', or 'check my PR'.	2 / 3
Distinctiveness Conflict Risk	'Code review' is a recognizable niche, but the broad scope ('code quality assurance', 'performance optimization', 'security vulnerabilities') overlaps with general development and security skills, so it could trigger for related skills.	2 / 3
	Total	8 / 12 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: e63f7dd

Reviewed: about 4 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.