evaluate-product

name	evaluate-product
description	Use when a built product needs scoring across conversion, revenue, UX, performance, accessibility, completeness, and code quality. Chains existing audit skills into a composite 0-100 score with AI-simulated user journeys.

Evaluate Product

Chain existing audit skills and AI-simulated user journeys into a composite product score (0-100). Produces structured JSON for machine consumption and a human-readable markdown report.

This is the entry point for the evolution loop. Run after a product is built (or after a previous optimization is deployed) to establish the current baseline and identify weak areas.

Instructions

CRITICAL — NON-INTERACTIVE: Execute all steps without pausing. Never ask questions, request confirmation, or wait for input. Read state, evaluate, score, write output, update state, stop.

---

Step 0: Initialize

1. Check if factory/evolution-state.json exists:

   • If it exists, read it. Set CYCLE to current_cycle. Update status to "evaluating". Write back.
   • If it doesn't exist, create the factory/ directory structure:

     mkdir -p factory/evaluations factory/hypotheses
     

     Create factory/evolution-state.json:

     {
       "version": 1,
       "project": "[from CLAUDE.md]",
       "status" 
        
        
             
        
        
        
     
     

     Set to .