skill-learning

To extract reusable methods, identify repeatable patterns from multi-step problem solving and apply context mining to turn tacit knowledge into structured, shareable skills. This captures workflows to reduce repeated effort and accelerate onboarding.

Knowledge capture for retrospectives works by mining completed tasks to identify repeatable method patterns, checking for duplicates, and formally evaluating candidates to build a growing catalog of shareable, reusable workflow skills.

The best way to document tacit know-how is to apply a formal evaluation process with frontmatter-driven metadata and structured sections, confirming extracted candidate methods to build an organized, growing skills catalog for future reuse.

No specific frameworks or dependencies are required to start. You simply describe a recent complex method you used and initiate the workflow to capture it, making it accessible for ongoing knowledge harvesting without technical prerequisites.

To avoid creating redundant skills, the workflow performs duplicate checks during context mining to ensure extracted methods are unique. This prevents redundant knowledge capture and maintains a clean, reusable skills catalog.