PluginBench
Skill
Pass
Audit score 90

design-first-ui-prompting

mengto/skills

Design-system-driven prompts for consistent, spec-first UI generation.

What is design-first-ui-prompting?

This skill teaches you to write tight, skimmable prompts that produce consistent UI outputs by treating prompts like design systems rather than wishes. Use it when you need reproducible, hierarchy-driven UI generation with locked typography, spacing, and color rules.

  • Structure prompts with goal, format, layout, type system, color, imagery, and copy sections
  • Lock one design system then iterate by changing only one variable at a time
  • Use constraints cards to anchor style rules and prevent drift across generations
  • Apply 2-pass workflow for reliable typography when text rendering is inconsistent
  • Build local reference packs to maintain taste and style consistency across iterations

How to install design-first-ui-prompting

npx skills add https://github.com/mengto/skills --skill design-first-ui-prompting
Claude Code
Cursor
Windsurf
Cline

How to use design-first-ui-prompting

  1. 1.Copy the provided prompt skeleton (GOAL, FORMAT, LAYOUT, TYPE SYSTEM, COLOR, IMAGERY, COPY, CONSTRAINTS, NEGATIVE PROMPT)
  2. 2.Fill in each section with explicit values (hex colors, font names, grid systems, exact copy lines)
  3. 3.Generate the first output focusing on layout, hierarchy, and copy accuracy
  4. 4.Create variants by changing only ONE variable (color, angle, spacing) per iteration
  5. 5.Use the fast iteration checklist to identify what to tweak next (spacing, contrast, hierarchy, texture)

Use cases

Good for
  • Generating landing page heroes with locked hierarchy and typography
  • Creating onboarding flows where spacing and contrast must stay consistent
  • Producing carousel slides or dashboard layouts that maintain a unified visual system
  • Iterating accent colors or background tones while keeping layout and type locked
  • Building UI variants (minimal vs glass vs playful 3D) from a single base spec
Who it's for
  • Product designers working with AI to generate UI mockups
  • Design engineers building design systems and component specs
  • Teams needing reproducible, spec-driven UI outputs
  • Anyone iterating UI designs where consistency across variants matters

design-first-ui-prompting FAQ

Why lock one system first instead of tweaking everything?

Changing multiple variables at once makes it impossible to know what caused a drift. Lock layout and hierarchy, then iterate one constraint at a time for predictable results.

What's the 2-pass workflow for typography?

If the model keeps misspelling or mangling text, generate the layout without text first (leaving clean text-safe areas), then typeset the final copy in Figma or your design tool.

How do I prevent the model from adding extra elements I didn't ask for?

Use a NEGATIVE PROMPT section listing what to exclude (no logos, no watermarks, no extra text beyond provided lines, no gibberish typography).

Should I use a reference pack?

Yes. Save style references into a local folder and point prompts to them instead of asking the model to 'remember' taste. This anchors consistency without relying on context memory.

What's the difference between this and regular UI prompting?

This treats prompts like design systems with locked constraints and explicit rules, rather than loose wish lists. It prioritizes hierarchy, typography, and spacing as first-class concerns.

Full instructions (SKILL.md)

Source of truth, from mengto/skills.


name: design-first-ui-prompting description: Use when you need design-first, spec-driven, skimmable prompts for UI generation. Covers prompt structure, constraints, variations, typography/spacing rules, and iteration workflow for consistent UI outputs.

Design-First UI Prompting Skill

This skill is for design-first prompting: turn fuzzy ideas into a tight spec that produces consistent UI.

Core principle

Prompt like a design system, not a wish.

Prompt Structure (copy/paste)

Use this skeleton, then fill the blanks.

GOAL
- What are we making? (e.g., landing page hero / onboarding / dashboard / carousel slide)
- Who is it for? (persona)
- What’s the success criteria? (clarity, conversion, vibe)

FORMAT
- Size/aspect: (e.g., 1080x1350)
- Safe margins: (e.g., 90px)

LAYOUT (wireframe in words)
- Grid: (e.g., Swiss 6-col)
- Placement: (e.g., type-left / image-right)
- Hierarchy: H1 → subhead → body → CTA

TYPE SYSTEM
- Font vibe: (e.g., Söhne / Neue Haas / SF Pro)
- Weights: (H1 700, body 400)
- Leading: (tight for H1, readable for body)
- Tracking: (micro labels wider)

COLOR + MATERIAL
- Background: (hex or description)
- Text: (white/ivory/charcoal)
- One accent only: (cyan/lime/purple)
- Texture: (subtle grain, no plastic HDR)

IMAGERY / UI STYLE
- UI style: (minimal / glass / editorial / playful 3D)
- If photo: lighting + crop + texture rules
- If 3D: materials + lighting + softness

COPY (render EXACTLY)
- Line 1:
- Line 2:
- ...

CONSTRAINTS (change 1–2 things only)
- FONT: ___
- STYLE: ___
- MODE: ___

NEGATIVE PROMPT
- No logos, no watermarks
- No extra text beyond provided lines
- No gibberish typography

Rules that improve consistency

1) Lock one “system”, then iterate with variants

  • First output: nail layout + hierarchy + copy.
  • Variants: change ONE variable at a time:
    • angle / crop
    • accent color
    • card arrangement
    • background tone

2) Treat typography as fragile

If the model keeps misspelling:

  • Use 2-pass workflow:
    1. Generate without text (reserve a clean text-safe area)
    2. Typeset in Figma

3) Use “constraints cards”

When you want the model to obey a style:

  • Add a small “Constraints” panel with explicit values.
  • It anchors the output like a mini style guide.

Example:

Constraints
FONT  CANELA
STYLE  MINIMAL
MODE  DARK

4) Keep a local reference pack

Don’t ask the model to “remember” taste.

  • Save references into a gitignored local reference folder, such as refs/...
  • Point prompts to the reference style

Fast iteration checklist (what to tweak)

  • Spacing: margins, leading, baseline rhythm
  • Contrast: background vs text
  • Hierarchy: one hero line, one support line
  • One accent only (don’t rainbow)
  • Texture: add grain, remove smoothing

Questions to ask (when user is vague)

  • What’s the single message of this screen?
  • What’s the hierarchy (H1 / sub / CTA)?
  • Which style lane: minimal editorial vs playful 3D vs glass UI?
  • Any must-keep constraints (font vibe, color, spacing, grid)?