run-tests

The 'run-tests' skill is a comprehensive framework designed to streamline the process of running, debugging, and verifying pytest test suites. It addresses the challenges developers face when handling test failures, complex debugging scenarios, or broken tests in large codebases. By integrating a structured investigation workflow with external AI tool consultation, this skill helps ensure that test failures are analyzed efficiently and resolved systematically, reducing trial-and-error efforts and improving overall development productivity.

Key capabilities of the skill include running tests with multiple presets such as quick runs, debug mode, and coverage analysis, as well as discovering and analyzing test structure. It emphasizes a hypothesis-driven investigation approach, encouraging users to analyze failures before consulting external tools. The skill also supports multi-agent analysis for complex issues, mandatory consultation with AI tools for test failures, and strategies for capturing and verifying test outputs. It provides clear guidance for long-running operations, ensuring that commands are executed in a way that avoids output spam and maintains user experience.

This skill is particularly useful for Python developers, QA engineers, and DevOps professionals who work with pytest-based testing environments. Typical use cases include debugging failing test suites, verifying bug fixes, analyzing unexpected exceptions, and running systematic investigations of complex or unclear test failures. It is ideal for teams that require a structured, repeatable approach to testing and debugging, where consistent consultation with AI tools can accelerate problem resolution and improve code reliability.