plugins/pm-design/skills/design-critique/SKILL.md
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.
npx skillsauth add mohitagw15856/pm-claude-skills design-critiqueInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides structured, actionable design feedback using established UX frameworks. It balances positive observations with clear, prioritised improvement suggestions.
Ask the user for these if not provided:
User goal: [What the user needs to accomplish] Context: [Platform / Stage] Critique focus: [Primary concern if stated, otherwise "full review"]
[3–5 specific, honest observations about what the design does well. Don't manufacture praise — only include genuine strengths. Be specific: "The visual hierarchy clearly guides the eye from headline → supporting detail → CTA" is useful. "Looks clean" is not.]
Rank issues by impact on the user goal. Use:
For each issue:
What's happening: [Describe the specific design problem — be precise about which element, screen, or interaction]
Why it matters: [Connect to the user goal or a specific principle — don't just say "it's confusing." Say why it creates confusion and what the consequence is for the user.]
Framework reference: [Name the principle being violated — e.g. Nielsen's Heuristic #6 (Recognition over Recall), Gestalt proximity, JTBD clarity, Fitts's Law, etc.]
Recommendation: [Specific, actionable suggestion. Not "make the button bigger" but "Increase the primary CTA to at least 44x44px to meet touch target guidelines; consider moving it below the form rather than inline with the input fields to reduce accidental taps."]
Quick assessment against Nielsen's 10 Usability Heuristics — score each as ✅ Pass / 🟡 Partial / ❌ Fail:
| Heuristic | Status | Note | |---|---|---| | 1. Visibility of system status | | | | 2. Match between system and real world | | | | 3. User control and freedom | | | | 4. Consistency and standards | | | | 5. Error prevention | | | | 6. Recognition rather than recall | | | | 7. Flexibility and efficiency of use | | | | 8. Aesthetic and minimalist design | | | | 9. Help users recognise, diagnose, and recover from errors | | | | 10. Help and documentation | | |
Only include heuristics relevant to what's visible in the design — don't penalise for things not in scope.
[Comment on any Gestalt principles that are either well-applied or violated:]
[Assess how well the design serves the stated job-to-be-done:]
Prioritised list of the 3 most impactful changes. Each should be actionable in the next design iteration:
business
Analyze why deals are won and lost and turn it into an action plan. Use when asked to run a win/loss analysis, review closed-won and closed-lost deals, understand why the team is losing to a competitor, or summarize sales feedback into patterns. Produces a structured win/loss report with themes, win/loss rates by segment and competitor, representative quotes, and prioritized actions for product, marketing, and sales.
development
Route a fuzzy request to the right skill in this library. Use when the user is unsure which skill fits, asks 'which skill should I use for X', describes a task without naming a skill, or when a request could plausibly match several skills. Produces a best-fit recommendation with the inputs to gather, a runner-up with the tie-breaker, and a workflow recipe when the job spans multiple skills.
testing
Triage a vulnerability or scanner finding — assess real severity, exploitability, and how urgently to fix. Use when asked to triage a CVE, prioritize scanner/pentest findings, assess a vuln's risk, or decide what to patch first. Produces a triage verdict: CVSS-informed severity adjusted for your context, exploitability, real risk, a fix/mitigation, and an SLA — so you fix what matters, not just what's red.
development
Stand up a Voice of Customer (VoC) program that turns feedback into action. Use when asked to build a VoC program, design a customer feedback loop, consolidate feedback sources, or set up a closed-loop feedback process. Produces a VoC program design — objectives, feedback sources and channels, a taxonomy, collection and analysis cadence, closed-loop routing, ownership, and success metrics.