Project overview
Skill Optimizer separates the agent-skill lifecycle into three workflows. skill-miner examines agent history, memories, archives, and repeated tasks for evidence-backed candidates; skill-personalizer adapts skills to a user's phrasing, tools, paths, and verification habits; skill-generalizer removes private context for public distribution. It also audits undertriggering, noisy activation, unnecessary questions, conflicts, and token costs. A deterministic scanner supports session data from Codex, Claude Code, Gemini, and exported transcripts.
Repository facts
- Primary language
- Python
- License
- MIT
- Repository updated
- Jul 14, 2026
- Default branch
- main
Resource types
Collection or directory
Use cases
Software development
Platforms
Claude CodeCursorGemini CLICodexOpenCode
Runtime
Local
Capabilities
Verification and evals