CtrlK
BlogDocsLog inGet started
Tessl Logo

code-reviewer

Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then produces a structured review report with prioritized, actionable feedback. Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues. Invoke for PR reviews, code quality checks, refactoring suggestions, review code, code quality. Complements specialized skills (security-reviewer, test-master) by providing broad-scope review across correctness, performance, maintainability, and test coverage in a single pass.

93

1.14x
Quality

92%

Does it follow best practices?

Impact

93%

1.14x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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 an excellent skill description that hits all the marks. It provides highly specific capabilities with concrete examples, includes explicit 'Use when' and 'Invoke for' trigger clauses with natural user language, and thoughtfully distinguishes itself from complementary specialized skills. The description is comprehensive yet not overly verbose, using proper third-person voice throughout.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: analyzes code diffs, identifies bugs, security vulnerabilities (with examples like SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, architectural concerns, and produces a structured review report with prioritized feedback.

3 / 3

Completeness

Clearly answers both 'what' (analyzes diffs/files to identify bugs, vulnerabilities, code smells, produces structured report) and 'when' (explicit 'Use when reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, or checking for security issues'). Also includes an 'Invoke for' clause with additional trigger terms.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'pull requests', 'PR reviews', 'code quality', 'refactoring', 'security issues', 'review code', 'code quality checks', 'refactoring suggestions'. These are terms users would naturally use when requesting code review.

3 / 3

Distinctiveness Conflict Risk

Clearly carves out its niche as a broad-scope code reviewer and explicitly differentiates itself from related specialized skills (security-reviewer, test-master), explaining it provides cross-cutting review in a single pass. The specific mention of diffs, PRs, and structured review reports makes it distinct.

3 / 3

Total

12

/

12

Passed

Implementation

85%

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

This is a well-structured code review skill with strong workflow clarity, excellent progressive disclosure via the reference table, and actionable code examples. Its main weakness is moderate verbosity—some sections restate obvious knowledge (SOLID/DRY acronyms, basic behavioral constraints) and the 'When to Use' section is redundant with the skill description. Overall it's a high-quality skill that effectively guides Claude through a structured review process.

Suggestions

Remove the 'Knowledge Reference' line at the bottom—Claude already knows SOLID, DRY, OWASP Top 10, etc. and listing acronyms adds no actionable value.

Trim the MUST NOT DO list to remove items Claude inherently follows (e.g., 'Be condescending or rude') and merge the remaining items into the workflow or constraints more concisely.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary content like the 'When to Use This Skill' section (which largely restates the description) and the 'Knowledge Reference' line at the end which just lists acronyms Claude already knows. The quick reference examples are valuable but the MUST DO/MUST NOT DO lists contain some obvious items (e.g., 'Be condescending or rude').

2 / 3

Actionability

Provides concrete, executable code examples for common issues (N+1 queries, magic numbers, SQL injection) with clear bad/good comparisons. The workflow steps include specific questions to ask, the output template gives a concrete structure, and the reference table points to detailed guidance files.

3 / 3

Workflow Clarity

The 5-step core workflow is clearly sequenced with an explicit checkpoint at step 1 (summarize intent before proceeding, ask for clarification if unable). Step 5 includes a feedback loop note about surfacing critical issues immediately. The disagreement handling note adds a valuable edge-case workflow. The output template provides a clear validation structure with a final verdict.

3 / 3

Progressive Disclosure

Excellent use of progressive disclosure with a clear reference table that specifies when to load each detailed reference file. The main skill provides a concise overview with quick-reference patterns inline, while deferring detailed checklists, examples, and templates to one-level-deep reference files with clear navigation signals.

3 / 3

Total

11

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Repository
jeffallan/claude-skills
Reviewed

Table of Contents

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.