code-review

Conduct thorough, constructive code reviews for quality and security. Use when reviewing pull requests, checking code quality, identifying bugs, or auditing security. Handles best practices, SOLID principles, security vulnerabilities, performance analysis, and testing coverage.

1.03x

Quality

88%

Does it follow best practices?

Impact

98%

1.03x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a well-crafted skill description that follows best practices. It uses third person voice, provides specific capabilities, includes an explicit 'Use when...' clause with natural trigger terms, and clearly distinguishes itself as a code review skill. The description covers both the what and when comprehensively.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'reviewing pull requests', 'checking code quality', 'identifying bugs', 'auditing security', plus mentions specific concepts like 'SOLID principles', 'security vulnerabilities', 'performance analysis', and 'testing coverage'.	3 / 3
Completeness	Clearly answers both what ('Conduct thorough, constructive code reviews for quality and security') and when ('Use when reviewing pull requests, checking code quality, identifying bugs, or auditing security'). Has explicit 'Use when...' clause with clear triggers.	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'code reviews', 'pull requests', 'code quality', 'bugs', 'security', 'best practices', 'SOLID principles', 'performance', 'testing coverage'. Good coverage of terms developers naturally use.	3 / 3
Distinctiveness Conflict Risk	Clear niche focused specifically on code review activities with distinct triggers like 'pull requests', 'code review', 'auditing security'. Unlikely to conflict with general coding skills or documentation skills due to specific review-focused language.	3 / 3
	Total	12 / 12 Passed

Implementation

77%

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

This is a thorough code review skill with excellent actionability and clear workflow structure, but it suffers from verbosity by explaining concepts Claude already knows (SOLID, common security vulnerabilities, basic anti-patterns). The content would benefit from being split into referenced sub-files rather than presenting everything inline, and the empty example sections at the end indicate incomplete work.

Suggestions

Remove explanations of concepts Claude already knows (SOLID principles, what SQL injection is, basic anti-patterns) and focus on project-specific conventions or novel guidance

Split detailed checklists into separate referenced files (e.g., SECURITY_CHECKLIST.md, PERFORMANCE_CHECKLIST.md) to reduce the main skill's token footprint

Complete the empty example sections at the end or remove them entirely

Consider condensing the extensive checklists into a more compact format, trusting Claude to expand on items as needed

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but verbose, including many concepts Claude already knows (SOLID principles, basic security concepts, what SQL injection is). The extensive checklists and explanations of well-known anti-patterns add token overhead without providing novel guidance.	2 / 3
Actionability	Provides concrete, executable code examples throughout (SQL injection fixes, XSS prevention, test naming conventions, documentation format). The checklists are specific and actionable, and code examples are copy-paste ready.	3 / 3
Workflow Clarity	Clear 8-step sequential process from understanding context through providing feedback. Each step has explicit sub-tasks, and the feedback section includes prioritization levels (🔴🟡🟢) for issue severity. The workflow is well-structured for a review process.	3 / 3
Progressive Disclosure	Content is mostly monolithic with everything inline. References to external resources exist at the end, but the skill itself is a wall of checklists and examples that could be split into separate files (security-checklist.md, anti-patterns.md, etc.). The empty example sections at the end suggest incomplete structure.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: supercent-io/skills-template
Commit: c033769

Reviewed: 15 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.