Is the Critique skill free?

Yes. The skill itself is free from educlopez/ui-craft. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Critique SkillProof Score?

8.4/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.

How do I install Critique?

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 Critique 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.

Critique

Screenshots your UI at 3 viewports and scores it against a named anti-slop checklist.

by educlopez · educlopez/ui-craft

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 8f8a497

Fed it a deliberately slop-y test page (purple-gradient hero, ALL CAPS heading, 3 identical emoji cards, colored trend pill) — it named all 4 critical anti-slop violations by the skill's own vocabulary and, because it forces real screenshots at 3 viewports, caught a genuine mobile overflow bug (the heading text spilling outside the hero background at 375px) that a code-only pass would have missed entirely.

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

Installs cleanly 3/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 4/5

What Critique does

A design-review lens that forces a real visual capture (desktop/tablet/mobile, dark mode if present) before judging a UI, then runs it through named anti-slop, craft, hierarchy, clarity and signature-detail checks, output as a Before/After/Why table. It is one lens of the broader ui-craft skill and is meant to be invoked when a user wants a design critique, a second opinion before handoff, or asks "what's wrong with this UI" — it does not edit code.

How to install Critique

git clone https://github.com/educlopez/ui-craft
cd ui-craft
mkdir -p ~/.claude/skills
cp -r .agents/skills/critique ~/.claude/skills/critique

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Critique

/critique Screenshots your UI at 3 viewports and scores it against a named anti-slop checklist.

It also activates on plain-language prompts like these:

Give me a design critique of this UI before we hand it off
Screenshot this page at a few viewports and score it against best practice
I want a second opinion on how polished this interface looks

Frequently asked questions

Is the Critique skill free?: Yes. The skill itself is free from educlopez/ui-craft. SkillProof publishes the install command and an independent test verdict at no cost.
Does Critique work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Works with setup. Fed it a deliberately slop-y test page (purple-gradient hero, ALL CAPS heading, 3 identical emoji cards, colored trend pill) — it named all 4 critical anti-slop violations by the skill's own vocabulary and, because it forces real screenshots at 3 viewports, caught a genuine mobile overflow bug (the heading text spilling outside the hero background at 375px) that a code-only pass would have missed entirely.
What is the Critique SkillProof Score?: 8.4/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.
How do I install Critique?: 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 Critique 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.