skill-validator

Automate skill validation by running multi-phase testing that includes static code analysis, AI semantic review, and dynamic execution testing to ensure quality and security. This process verifies structural integrity, path safety, script quality, and cross-platform compatibility before deployment.

Pre-release skill acceptance testing checks OpenClaw skills for structural adherence, path safety, script quality, cross-platform compatibility, reference integrity, and size constraints. It combines static analysis with AI-driven semantic review and dynamic execution testing to ensure comprehensive safety.

Yes, you need PyYAML and py_compile dependencies to run automated code reviews on skills. These dependencies enable the validation scripts to perform static analysis and parse YAML configurations during the multi-phase testing process.

Yes, you can use automated testing for regression testing of skill updates. The validation process performs dynamic execution testing and static analysis to catch structural, path safety, and reference integrity issues that may arise from modifying existing skills.

The best way to ensure cross-platform compatibility and reference integrity is through comprehensive multi-phase validation. This approach verifies path safety, checks script quality, and validates reference integrity against size constraints to guarantee skills meet cross-platform standards.

Dynamic execution testing may fail during static analysis if skill scripts contain structural errors, path safety violations, or size constraint exceedances. The validation process isolates static code analysis from dynamic execution to accurately identify whether script quality or runtime behavior causes failures.