How does the Test Reviewer output its findings?

It generates a structured report including a coverage ratio, a list of specific behaviors checked, categorized issues (Critical, Important, Suggestion), and a final 'Approved' or 'Needs Fixes' assessment.

Is this skill limited to specific programming languages?

The Test Reviewer is language-agnostic. It applies general TDD best practices and uses your project's CLAUDE.md file to understand specific language rules and API usage.

What are 'default-value traps' in testing?

Default-value traps occur when a test asserts a falsy or zero value (like false, nil, or 0) that a stub would return by default. These tests can pass even if the logic is broken, and the Test Reviewer flags them as invalid.

Does the Test Reviewer write or modify code?

No, the Test Reviewer is strictly an auditing tool. It reports findings and provides a structured assessment but does not modify any files or write implementation code.

Test Reviewer

Name: Test Reviewer
Author: kelp

bykelp

•

安全与测试

Audits unit and integration tests to ensure comprehensive coverage, behavioral correctness, and robust test design.

The Test Reviewer is a specialized Claude Code skill designed for the TDD workflow, specifically focused on auditing test suites generated by automated agents. It rigorously evaluates tests for behavioral alignment with specifications, identifies missing edge cases, and flags 'default-value traps' where tests might pass falsely due to uninitialized stubs. By providing a structured assessment without modifying code, it serves as an automated quality gate that ensures tests are independent, meaningful, and truly reflective of the intended system behavior across any programming language.

主要功能

01Detection of 'default-value traps' to prevent false-positive test results

02Comprehensive coverage analysis against technical specifications and edge cases

03Language-specific context awareness based on project-level CLAUDE.md guidelines

042 GitHub stars

05Validation of test independence and proper resource setup/teardown

06Strict behavior-based verification focused on outcomes rather than implementation details

使用场景

01Enforcing TDD best practices and test quality standards across a development team

02Performing automated code reviews focused specifically on test reliability and maintenance

03Auditing AI-generated test suites for logic errors and missing scenarios

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add kelp/kelp-claude-plugins test-reviewer

For use in Claude.ai and ChatGPT

主要功能

01Detection of 'default-value traps' to prevent false-positive test results

02Comprehensive coverage analysis against technical specifications and edge cases

03Language-specific context awareness based on project-level CLAUDE.md guidelines

042 GitHub stars

05Validation of test independence and proper resource setup/teardown

06Strict behavior-based verification focused on outcomes rather than implementation details

使用场景

01Enforcing TDD best practices and test quality standards across a development team

02Performing automated code reviews focused specifically on test reliability and maintenance

03Auditing AI-generated test suites for logic errors and missing scenarios

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add kelp/kelp-claude-plugins test-reviewer

For use in Claude.ai and ChatGPT