CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review-assistant

Conduct comprehensive code reviews identifying bugs, security issues, performance problems, code quality concerns, and best practice violations. Use when reviewing pull requests, examining code changes, evaluating new code, assessing code quality, or providing feedback on implementations. Analyzes code for correctness, security vulnerabilities, performance bottlenecks, maintainability issues, test coverage, documentation quality, and adherence to coding standards. Produces structured markdown reviews with categorized findings, severity ratings, specific examples, and actionable recommendations. Triggers when users ask to review code, check pull requests, evaluate implementations, find bugs, or assess code quality.

88

1.25x
Quality

88%

Does it follow best practices?

Impact

83%

1.25x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

40%

User Authentication Module Review

Review template structure and severity categorization

Criteria
Without context
With context

Summary section present

58%

100%

Critical severity section

100%

100%

Important severity section

0%

100%

Minor severity section

0%

100%

Suggestion section

0%

100%

Issue location provided

100%

100%

Issue impact explained

100%

100%

Recommendation with code example

100%

100%

Positive Observations section

41%

100%

Questions for Author section

0%

100%

Overall verdict

40%

100%

85%

Survey Data Processor Review

Python anti-patterns and security review

Criteria
Without context
With context

Mutable default argument

100%

100%

Bare except clause

100%

100%

String concatenation in loop

0%

0%

SQL injection vulnerability

100%

100%

SQL injection severity

100%

100%

Python fix examples

100%

100%

Issue locations

100%

100%

66%

12%

Order Processing Service Review

Code quality standards, naming conventions, and testing review

Criteria
Without context
With context

Function length violation

0%

0%

Excessive nesting depth

100%

90%

Boolean naming convention

0%

0%

Function/variable naming

0%

87%

Loose equality operator

100%

100%

Unhandled promise

100%

100%

Missing test coverage

100%

83%

Test naming quality

100%

100%

AAA pattern or test structure

0%

0%

Severity classification

20%

100%

Repository
ArabelaTso/Skills-4-SE
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.