Your AI coding agent already writes code. This makes it think like a CTO. Dual-agent review, circuit breakers, design gates, session memory. For Claude Cowork + OpenAI Codex.

5-dimension engineering taste skill for Claude Code — evaluate code, architecture, product, design, and communication quality with calibrated judgment

the frontend craft specification. 324 rules. 20 categories. every threshold is a number, not an opinion.

Browser-first design quality scanner. Opens real pages in Playwright, measures actual pixels, catches AI slop patterns. Fixes them too.

A taste system for AI agents. 288 skills, 80 agents, 12 rules, and 8 hooks that turn generic AI output into work with genuine design quality. Anti-slop detection, typography craft, color systems, brand voice, product strategy, and 50+ specialized reviewers across UI, industry, platform, and content domains.