suggest-skills

Conversation pattern recognition audits chat history to detect repeated tasks, frustrations, and workarounds. By extracting these recurring methodologies, it identifies actionable opportunities for new skill generation and workflow automation.

The best way to suggest new skills from conversation analysis is by cross-checking identified patterns against an existing skill database. This comparison generates structured proposals for new skills, improvements to current ones, and areas where skills aren't needed.

Auditing chat history to find skill improvement areas involves reviewing conversation turns for reinvented processes or workarounds. Comparing these patterns against existing skills reveals gaps and generates targeted proposals for skill enhancements or new skill creation.

Yes, conversation analysis for skill suggestion works without dependencies. This meta-skill independently processes various conversation structures to extract patterns and propose actionable skillification suggestions without requiring external modules or frameworks.

When extracting patterns from conversation data, expect a structured list of outputs containing proposals for new skills, improvements to existing skills, educational opportunities, and not-worth proposals identifying areas where skill creation is unnecessary.