Design Review Cowork

Multi-lens prototype review (UX, a11y, frontend, critic) into a prioritized, fix-ready rep

Tested · Works

Test report

Verdict
Tested · Works
Score
8.8/10
Tested
Jul 20, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · 2348c00

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 20, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Built a sign-in prototype with 12 planted defects and reviewed it twice. A natural no-skill pass caught 7 of 12 with no prioritization; following the skill's multi-lens structure caught all 12, adding the exact accessibility items a quick pass skips -- heading order, an unannounced aria-live error, missing prefers-reduced-motion, and absent focus indicators -- plus CRITICAL/HIGH/MEDIUM tiers and eight WCAG criterion citations with fix snippets. One honesty caveat: loaded into a single Claude session it role-plays the reviewers sequentially rather than spawning the parallel Batch-API agents the docs describe, though the frontmatter does disclose that dependency.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 4/5

What Design Review Cowork does

Reviews an HTML/React/screenshot prototype from several expert lenses at once (Senior UX, Accessibility Specialist, Frontend Engineer, Design Critic, plus optional performance/brand/strategy) and returns one prioritized report with WCAG-mapped, Claude-Code-ready fix instructions. Triggers when you have built a prototype and want expert critique before shipping.

How to install Design Review Cowork

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Design Review Cowork

  • /design-review-cowork Multi-lens prototype review (UX, a11y, frontend, critic) into a prioritized, fix-ready rep

It also activates on plain-language prompts like these:

  • Review this prototype from UX, accessibility, and frontend angles
  • Give me a prioritized, fix-ready critique of this React component
  • Check this HTML mockup for WCAG issues before we ship it to users

Frequently asked questions

Is the Design Review Cowork skill free?
Yes. The skill itself is free from matthewlarn/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Design Review Cowork work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Tested · Works. Built a sign-in prototype with 12 planted defects and reviewed it twice. A natural no-skill pass caught 7 of 12 with no prioritization; following the skill's multi-lens structure caught all 12, adding the exact accessibility items a quick pass skips -- heading order, an unannounced aria-live error, missing prefers-reduced-motion, and absent focus indicators -- plus CRITICAL/HIGH/MEDIUM tiers and eight WCAG criterion citations with fix snippets. One honesty caveat: loaded into a single Claude session it role-plays the reviewers sequentially rather than spawning the parallel Batch-API agents the docs describe, though the frontmatter does disclose that dependency.
What is the Design Review Cowork SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Design Review Cowork?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Design Review Cowork with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.