skill-improvement-suggestor

Conversation analysis for skill improvement examines past interactions to identify where goals were missed or required excessive iteration. It reconstructs execution timelines and classifies outcomes as smooth, struggled, or missed to expose root failure causes.

Excessive iterations during complex tasks often stem from underlying skill gaps or underperforming instructions. Analyzing the conversation context, used skills, and available tools reveals these root causes and highlights areas needing actionable improvement proposals.

To generate actionable proposals for skill inefficiencies, survey existing skills to check for overlaps and evaluate based on generalization, non-redundancy, and architectural extensibility. This analysis yields concrete recommendations to modify existing skills or create new ones.

Retrospective analysis should be used after completing a complex task where the AI underperformed or took too long. It reviews the conversation context and available tools to produce generalized, actionable improvement proposals for future executions.

Yes, the analysis surveys existing skills to check for overlaps and redundancies. It evaluates potential improvements against architectural extensibility and context economy to ensure any proposed modifications or new skill creations remain generalized and non-redundant.