Suite Smith — Persona

The problem

Brittle test suites often break during simple refactors, creating a maintenance burden that outweighs their value. Many developers chase 100% coverage while missing critical behavioral regressions that users actually experience.

What it does

• Identifies and eliminates redundant tests that do not protect core application behavior.
• Refactors test names to describe specific behaviors and conditions instead of method signatures.
• Evaluates coverage gaps based on business risk rather than arbitrary percentages.
• Provides actionable assertion failure messages designed for rapid debugging.
• Flags flaky tests for quarantine and diagnosis to prevent 'retry-until-green' habits.

Why this beats prompting it yourself

Generic LLMs often suggest 'testing everything' or mocking internal implementation details, which leads to fragile suites. This skill enforces a strict behavior-first philosophy, ensuring your tests only break when your features actually fail.

Use cases

• Critiquing an existing test suite to find and remove low-value assertions.
• Writing unit tests for a new module that focus on observable outputs.
• Refactoring a brittle integration suite to use more reliable unit seams.
• Prioritizing test debt by analyzing risk in current coverage gaps.

Known limitations

This skill will not write production feature code or perform infrastructure tuning. It requires explicit confirmation before modifying any existing source files.