36+ ChatGPT & Claude prompts for UX & Design

**Role:** Senior product designer who has shipped onboarding flows at 4 high-trust B2B SaaS. You think in funnel drop-off, not aesthetics.

**Context:** Product: [name + category]. Onboarding flow URL or screenshots: [paste/link]. Target user: [persona]. Their job-to-be-done: [the one they came to do]. Current activation rate: [%].

**Task:** Walk through the first 90 seconds of the flow and produce a friction audit.

1. List every step the user encounters in order. Number them.
2. For each step, identify: time-to-complete (estimated), cognitive load (low/med/high), and friction type if any (forced field, unclear copy, broken expectation, dead end).
3. Severity rating per friction point: [S1 = blocks activation] / [S2 = degrades activation] / [S3 = nit].
4. For S1/S2 issues, propose a specific fix — not "improve onboarding" but "remove the email verification step from the signup screen; move it to first dashboard load."
5. Surface the ONE thing that, if fixed, would move the activation needle the most.

**Constraints:**
- Never critique aesthetics unless they cause measurable friction
- Cite specific screen IDs or URLs
- Distinguish "this is unclear copy" from "this is missing entirely"
- Propose a hypothesis the team could A/B test for the top item

**Output format:** Numbered step audit table + S1/S2 fix proposals + "top single fix" callout · ≤900 words.

**Role:** UX writer who has owned every microcopy decision at a financial product where misunderstanding the validation costs the user real money.

**Context:** Form: [name — signup, payment, profile update]. Validation rules: [list each rule and the conditions]. Audience: [persona — assume varied technical comfort]. The validation strategy: [inline as-you-type | submit-then-show | hybrid].

**Task:** Write the validation microcopy for every field.

1. For each field, write: [field label] + [placeholder if any] + [success state if any] + [each error variant].
2. Error copy must answer 3 questions: WHAT went wrong + WHY it's wrong + WHAT to do.
3. Specific over general: "Password must include a number" beats "Invalid password."
4. Never blame the user. "We can't find that email — want to try signing up?" beats "Email not found."
5. For irreversible actions (delete, send money), use confirmation copy that names the specific consequence.

**Constraints:**
- Never use "Invalid" alone
- Never use exclamation points
- Use second person consistently
- Microcopy ≤12 words per error

**Output format:** Table per field — [Label] / [Placeholder] / [Success] / [Error variants] · plus 1-paragraph "tone notes" callout.

**Role:** Senior brand/product designer who's run 200+ design crits. You can tell from 10 feet away whether a screen's typography is doing the work.

**Context:** Screen: [paste / link to image]. Brand voice: [if known]. Stage: [draft | pre-ship | post-mortem]. Frame: [marketing landing page | product dashboard | onboarding step].

**Task:** Critique the typography in priority order.

1. Hierarchy: does the user's eye land on the right thing first? If no, what's competing?
2. Scale: are jumps between text sizes meaningful (≥1.25 ratio)? Identify any noise — labels and metadata fighting for attention.
3. Weight: are weights doing semantic work (headings, body, captions) or just visual variety?
4. Leading: is line-height ≥1.4 for body? ≥1.1 for display? Flag any "tight" body text.
5. Optical alignment: are baselines aligned across columns? Are vertical rhythms intact?
6. Contrast: is body text ≥4.5:1 against background? Are captions ≥3:1?

**Constraints:**
- Cite specific elements ("the secondary nav metadata") not regions ("the top area")
- Always propose a specific change ("drop body from 16/24 to 15/22 to free up vertical rhythm") not "improve hierarchy"
- Don't critique color choices unless they cause readability issues
- Rank issues: must-fix, should-fix, nice-to-fix

**Output format:** 6 numbered sections + ranked issue list · ≤700 words.