What problem does it solve?
This Skill helps you create high-quality behavioral tests for a source file or module without drifting into brittle implementation checks, weak assertions, or framework-level noise. It adds a structured review loop so generated tests are not just fast to produce, but also meaningful, maintainable, and aligned with domain behavior.
Core Features & Use Cases
- Behavior-first test generation: Reads the target code, identifies public interfaces, decision points, error modes, and external boundaries, then generates tests around what the code actually does.
- Iterative quality review: Runs a reviewer feedback loop to catch overly coupled tests, unnecessary mocks, weak naming, and missing outcome-based assertions before finalizing.
- Verification and safety guardrails: Executes the resulting test file, limits retry cycles, and explicitly avoids weakening assertions just to make tests pass.
- Use cases: Ideal when you need tests for a business-logic module, want to add coverage for a new class or function, or need to review existing tests to ensure they validate behavior rather than internals.
Quick Start
Ask the AI to use test-forge on a specific source file or module path to generate and verify behavioral tests for that code.
