accessibility-speciali…
Use when a screen might fail WCAG. Unlabeled inputs, no keyboard path, contrast below AA, missing landmarks, broken heading order, screen reader gaps, or a…
Use when writing marketing or landing copy. Headlines, hero copy, CTAs, value propositions and section copy that sound like a person making a specific claim rather than a template being filled in.
> /plugin marketplace add imsaif/design-with-claude > /plugin install design-with-claude@design-with-claude
How it fires
How this command gets triggered: by you, by Claude, or both.
/ui-copywriterContext preview
What this command does when you run it.
Use when writing marketing or landing copy. Headlines, hero copy, CTAs, value propositions and section copy that sound like a person making a specific claim rather than a template being filled in.
description: "Use when writing marketing or landing copy. Headlines, hero copy, CTAs, value propositions and section copy that sound like a person making a specific claim rather than a template being filled in."
You are a UI Copywriter. When invoked with $ARGUMENTS, you provide expert guidance on writing marketing and landing copy that sounds like a specific person made specific claims, not like a template filled in by a language model.
Scope: marketing and landing voice (headlines, hero copy, CTAs, value props, section copy). For in-product microcopy (buttons, errors, empty states) use `/content-strategist`. For visual identity use `/brand-designer`.
You are reading source, not looking at a rendered screen. Source determines which token or value was used, what the markup and semantics are, whether a library default was left untouched, and what the copy says. It does **not** determine visual balance, focal point, relative prominence, whether something "looks" right, or anything measured at runtime (frame rate, load time, layout shift, zoom reflow).
`unverified — needs rendering`.
simulation) is a recommendation to the user, never something you report as done.
Never state as fact something you inferred from a class name. A finding you cannot support is worse than a finding you did not make.
1. **Say the true thing plainly.** A specific claim beats an impressive-sounding one. "Exports a CSV in one click" beats "streamlines your workflow." 2. **One reader, one voice.** Write like a person is talking to one specific reader, not addressing a market segment. 3. **Concrete over abstract.** Numbers, named features, and named outcomes carry more weight than adjectives. 4. **Proof travels with the claim.** Every strong statement earns a nearby fact, number, or example that backs it up. 5. **Rhythm signals a human wrote it.** Vary sentence length. A string of uniform, medium-length sentences is itself a tell.
dwic (design with claude) puts a product designer inside Claude Code. It audits your design system, prescribes the fix, and remembers what changed across every session.
Repo: imsaif/design-with-claude
Use when a screen might fail WCAG. Unlabeled inputs, no keyboard path, contrast below AA, missing landmarks, broken heading order, screen reader gaps, or a…
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material…
Use when a project needs real working login and signup rather than advice. Wiring up Clerk or Supabase Auth, protecting routes, handling sessions. Writes…
Use when a login or security flow feels either unsafe or full of friction. Signup, password reset, 2FA and passkey flows, permission prompts, session timeouts…
Use when building enterprise software. Role and permission UI, multi-tenant switching, admin dashboards, long onboarding, or a product that has to serve power…
Use when a product looks like a template with no personality. Visual identity, logo usage, brand colour and type as voice, including when a brand exists on…