Can this skill identify specific types of tests like E2E or Integration?

Yes, Tester Detective can distinguish between unit, integration, and end-to-end tests by analyzing the testing patterns, frameworks, and summaries indexed in memory.

How do I ensure the test analysis is up to date?

You should run the 'claudemem status' command to check enrichment status and 'claudemem enrich' if the symbol summaries are missing or outdated.

Why does Tester Detective forbid using grep or find?

It utilizes claudemem v0.2.0 semantic indexing, which provides deeper context and understanding of code purpose through vector embeddings and LLM enrichment, offering far more accuracy than simple text matching.

What is a 'symbol_summary' in this context?

A symbol_summary is an LLM-generated document that describes what a specific test verifies, including its parameters and side effects, allowing the AI to understand the 'why' behind the test code.

Tester Detective

Name: Tester Detective
Author: MadAppGang

byMadAppGang

•

177

セキュリティとテスト

Performs deep test coverage analysis and QA audits using semantic indexed memory to identify missing edge cases and test quality issues.

概要

Tester Detective is a specialized QA-focused skill for Claude Code that replaces traditional text searching with semantic indexed memory via claudemem v0.2.0. It enables developers and QA engineers to map test infrastructure, identify coverage gaps, and surface complex code paths that lack verification. By leveraging LLM-generated symbol summaries, the skill understands the actual intent and purpose behind tests rather than just matching text, making it ideal for auditing large codebases for quality, testability, and critical boundary condition handling.

主な機能

Semantic Test Discovery: Locates unit, integration, and E2E tests using natural language queries instead of grep.
177 GitHub stars
Coverage Gap Identification: Cross-references implementation logic with existing test summaries to find untested paths.
Test Quality Analysis: Detects test smells such as missing assertions, over-mocking, or flaky async patterns.
Edge Case Audit: Specifically searches for missing boundary conditions, error handling, and race condition tests.
Indexed Memory Integration: Exclusively uses claudemem v0.2.0 enrichment for context-aware code analysis.

ユースケース

Auditing a legacy codebase to map out existing test coverage before beginning a major refactor.
Identifying critical business logic and API endpoints that lack error-path verification or boundary condition tests.
Generating a comprehensive test infrastructure report including frameworks, utilities, and mocking patterns for new team members.

概要

主な機能

Semantic Test Discovery: Locates unit, integration, and E2E tests using natural language queries instead of grep.
177 GitHub stars
Coverage Gap Identification: Cross-references implementation logic with existing test summaries to find untested paths.
Test Quality Analysis: Detects test smells such as missing assertions, over-mocking, or flaky async patterns.
Edge Case Audit: Specifically searches for missing boundary conditions, error handling, and race condition tests.
Indexed Memory Integration: Exclusively uses claudemem v0.2.0 enrichment for context-aware code analysis.

ユースケース

Auditing a legacy codebase to map out existing test coverage before beginning a major refactor.
Identifying critical business logic and API endpoints that lack error-path verification or boundary condition tests.
Generating a comprehensive test infrastructure report including frameworks, utilities, and mocking patterns for new team members.