Rate your task output against a structured five-axis rubric to catch gaps and improve quality.

Run a board memo or strategy brief through multiple model providers to reconcile divergences and achieve consensus.

Run structured UX evaluations, score findings against heuristics, and route issues to specialist skills.

Build, test, and evaluate Model Context Protocol servers for Python and TypeScript.

Build production ML systems with robust data contracts, reproducible training, and operational monitoring.

Iteratively improve skill frontmatter and routing test coverage with a structured compliance workflow.