Architecture Refinement Skill

Document AI cognitive architecture patterns by extracting recurring problem solutions and consolidating them into structured markdown files within the .github/ directory. This process uses pattern extraction templates to capture architectural learnings and process improvements for knowledge management.

Consolidate AI instruction sets by applying KISS and DRY principles to update or create skill files. A consolidation decision tree guides whether to merge new instructions into existing files or create standalone definitions, ensuring consistency and reducing redundancy in the knowledge base.

Markdown linting is required for AI prompt definitions and skill files in the .github directory. Adhering to markdown linting standards ensures quality assurance and structural consistency when documenting cognitive architecture updates and migrating trackers.

Create new instruction files when handling novel user requests that lack existing patterns, and update existing ones when refining known processes. A consolidation decision tree evaluates recurring requests to maintain architectural consistency and apply knowledge consolidation effectively.

Architecture refinement tracks file migrations and consolidations by updating dedicated trackers. This ensures that structural changes to instruction sets, prompt definitions, and skill files are logged, maintaining an accurate history of the AI's evolving cognitive architecture.

Pattern extraction templates for AI knowledge management require strict adherence to markdown linting and consolidation decision trees. Limitations include the need for manual session insight extraction and dependency on structured .github directory environments to properly document cognitive architecture.