tdd-guide

The tdd-guide skill is an advanced engineering tool designed to streamline the entire Test Driven Development (TDD) lifecycle for AI-powered coding agents. It provides a structured approach to writing, testing, and refining code by bridging the gap between business requirements and executable test suites. Designed for developers and engineering subagents, it excels at transforming user stories, API specifications, and business rules into high-quality test cases while ensuring architectural integrity across diverse environments.

• Intelligent Test Case Generation: Converts requirements, API schemas, and user stories into executable code, including test stubs, fixtures, and mock implementations.
• Comprehensive Coverage Analysis: Parses LCOV, JSON, and XML reports to identify untested paths, branch coverage gaps, and prioritize technical debt reduction.
• TDD Workflow Orchestration: Provides interactive, step-by-step guidance for the Red-Green-Refactor cycle, including automated validation and test quality scoring.
• Multi-Framework Adaptation: Native support for Jest, Pytest, JUnit, Vitest, Mocha, and RSpec, with automatic configuration of test runners and boilerplate creation.
• Metric-Driven Insights: Calculates cyclomatic complexity, cognitive complexity, and testability scoring to improve overall software design and maintainability.

Users can interact with the skill by providing source code, coverage reports, or requirement documents as direct file paths or copy-pasted text. The skill features automatic language detection for TypeScript, Python, Java, and JavaScript. Outputs are context-aware, providing rich markdown for desktop usage, JSON for CI/CD pipeline integration, or terminal-friendly reports for CLI workflows. It is highly recommended for teams aiming to maintain high test coverage, reduce flakiness in CI environments, and enforce consistent testing standards across polyglot repositories. The skill operates on a principle of progressive disclosure, delivering high-level summaries followed by granular, P0-P2 prioritized improvement recommendations.