When another agent or skill produces UI output, it can call this skill to get a structured design brief — real design tokens, color systems, typography, spacing — that transforms generic AI output into distinctive, intentional design.
Use these tools to generate a DESIGN.md for a given project or style:
ToolUsedesign-extractor.comPaste any URL → structured DESIGN.md with tokensdesign/promptsBrowse 31+ rendered design styles, grab AI promptstypeui.shnpx typeui.sh pull [style] — CLI, 57+ design skillsawesome-design-mdReal DESIGN.md files from Stripe, Linear, Vercel etc.
Stored in references/design-tokens.md:
text
Another agent requests design improvement
│
▼
1. Identify the output medium (HTML/React/Newsletter/PDF/etc.)
2. Identify the target aesthetic or reference site
3. Use design-extractor.com or typeui.sh to generate design tokens
4. Merge with references/design-tokens.md base system
5. Write a DESIGN.md into the project or skill directory
6. Downstream agents read DESIGN.md → apply consistently
Before any design is marked complete, run it through a VLM review iteration:
Apply design tokens → produce HTML/React/PDF/etc.
Use canvas tool to snapshot the rendered output:
text
canvas(action=snapshot, node=<target>, width=1280)
Send the snapshot to the vision model with the design brief:
text
Review this against the DESIGN.md tokens:
- Are colors consistent with the palette?
- Is typography on-scale (no arbitrary sizes)?
- Is spacing on the 8px grid?
- Are component states correct (hover, active)?
- Any visual anti-patterns (orphaned text, broken hierarchy)?
Flag specific issues and suggested fixes.
If VLM flags issues → apply fixes → resnapshot → re-review. Repeat until VLM returns "design is consistent with tokens" or all flagged issues resolved.
Only mark complete when VLM confirms token consistency. Log iteration count in the DESIGN.md.
text
Iteration log:
- v1: Initial render — 3 issues flagged (orphaned h3, wrong accent color, spacing off grid)
- v2: Fixed accent + orphaned h3 — spacing still off
- v3: All clear. Approved.
HTML/Newsletter:
text
Check: color palette, typographic hierarchy, spacing grid alignment,
component borders, dark/light mode if applicable. Flag any ad-hoc values.
PDF (rendered as screenshot):
text
Check: font sizes on scale, line spacing, margin consistency,
image placement, page break handling. Note any text overflow or orphans.
React/UI Component:
text
Check: button/input sizes match tokens, color applied from palette,
hover/active states visible, spacing between elements on grid.
bash
# Extract design from a reference URL
# (use design-extractor.com manually, paste result into project)
# Or pull a known style from typeui
npx typeui.sh pull minimal # clean typographic
npx typeui.sh pull editorial # magazine/longform
npx typeui.sh pull brutalist # high contrast, raw
npx typeui.sh pull luxury # dark, gold accents
0.3s without tokens)This skill is designed to be called by other skills. Any skill that produces visual output should reference this skill before generating UI.
See references/integration-guide.md for how other skills should call design-agent.
FilePurposereferences/design-tokens.mdBase design token systemreferences/integration-guide.mdHow other skills call design-agentassets/design-prompt-template.mdDESIGN.md template for new projectsassets/example-design-standards/Example extracted from Vercel/Linear/Stripe