Runs a multi-agent product audit by spawning parallel Claude Code tasks and optionally Codex CLI processes to analyze your codebase from different angles. It auto-detects what tools you have installed and scales accordingly, no setup prompts. You get quantified findings like "47 interactive elements on first screen" and "3 features with duplicate entry points" across UX, API, architecture, and docs. The synthesis phase cross-validates where agents agree or disagree, which is useful for catching blind spots. Supports scoped analysis (just UX, just API) and can invoke competitors-analysis for side-by-side comparison. Best for pre-launch audits or when you need hard numbers about complexity creep.
npx skills add https://github.com/daymade/claude-code-skills --skill product-analysis