What do I need to use Design Critique?

What is being reviewed; Design description or attached image; User goal; Context; Stage; Primary concern (optional).

Is Design Critique free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Design Critique

Q: How do I know the Design Critique output is good?

The skill verifies itself against its own quality checks: "What's working" includes only genuine, specific observations; Every issue has a framework reference (not just subjective opinion); Recommendations are specific and actionable; Priority levels (High/Medium/Low) reflect actual impact on user goal.

🔵 Stable🕐 updated 2026-06-24 🔷 SkillSpec L3 pm-design

Give structured, constructive feedback on any design using UX frameworks. Use when asked to critique a design, review a UI, give feedback on a Figma file or wireframe, assess a user flow, or evaluate a design against UX principles. Produces actionable critique applying Jobs-to-be-Done, Gestalt principles, and usability heuristics, with prioritised issues and specific recommendations.

📚 Based on Nielsen's usability heuristics

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

🗣 Say this to your agent

“Critique this design: [description or image]”“Give me feedback on this UI/UX”“Review this Figma screen for usability issues”“What's wrong with this user flow?”“Do a heuristic evaluation of [screen/product]”

What to give it

▸What is being reviewed — screen, flow, component, full product

▸Design description or attached image — describe it if no image — the skill will still work

▸User goal — what is the user trying to accomplish with this design?

▸Context — web / mobile / desktop app / physical product

▸Stage — early wireframe / mid-fidelity / high-fidelity / live product

▸Primary concern (optional) — optional — e.g. "I'm worried the onboarding is too long" or "I think the CTA is unclear"

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓"What's working" includes only genuine, specific observations

✓Every issue has a framework reference (not just subjective opinion)

✓Recommendations are specific and actionable

✓Priority levels (High/Medium/Low) reflect actual impact on user goal

✓Heuristic assessment only covers visible elements

⚠️ What it refuses to do

Do not lead with visual preference (e.g. "I don't like the colour") — every issue must reference a UX principle or user impact

Do not invent problems in the "What's Working" section — manufactured praise undermines the entire critique

Do not provide the same priority level (High/Medium/Low) to every issue — prioritisation requires genuine judgment about user impact

Do not skip the JTBD section for product screens — connecting feedback to the user's job-to-be-done is what separates UX critique from aesthetic opinion

Do not give recommendations that require a full redesign when the user is in high-fidelity — scope recommendations to the design stage

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="design-critique"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Design Critique is one of 1078 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog