manage-skills

Analyze session file changes against existing skill definitions to identify coverage gaps, invalid references, and outdated patterns. This detects missing verification skills by mapping changed files to current skill coverage and highlighting areas lacking verification.

AI skill lifecycle management involves analyzing session changes to dynamically discover, create, or update verification skills. It is needed to maintain code quality and consistency by ensuring verification skills stay up-to-date and comprehensive as features evolve.

Analyze the current session changes to map modified backend and frontend files to existing verification skills. User-guided decisions then facilitate updating the affected skills or creating new ones to ensure full coverage of the new feature changes.

Yes, you can automate code quality verification by orchestrating a workflow that maps changed files to existing verification skills. This coverage analysis highlights gaps and facilitates dynamic creation or updating of verification skills to maintain consistency.

Create new verification skills when coverage gap identification reveals that no existing skill definitions map to the changed files. User-guided decisions help determine whether to update an outdated pattern or create a completely new skill.

This approach focuses strictly on existing skill definitions and file changes, relying on user-guided decisions for updates. Unmapped files or changes outside the analyzed session may lack automated verification coverage, requiring manual skill creation.