Summary
A five-dimension design review system that scores any HTML artifact (deck, landing page, prototype) on Philosophy, Visual Hierarchy, Detail, Functionality, and Innovation. Returns a single-file HTML report with a radar chart, evidence-backed scores 0-10, and three action lists: Keep, Fix, Quick-wins. Born from the huashu-design expert-critique workflow. The scoring discipline is worth reading: don't average up broken pages, cite specific classes and line numbers, and don't grade-inflate. Works as a post-generation self-check loop or as a standalone audit when someone pastes code and asks "what's wrong with this?" Most useful when you need to defend a score or identify the highest-leverage 15-minute fixes.
Install to Claude Code
npx -y skills add nexu-io/open-design --skill critique --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
