/reference-interpreter
Triggers when user shares a screenshot, image, URL, or design description โ or says 'analyze this', 'make a brief', 'interpret this reference'. Outputs a structured Design Brief mapping visual intent to design system tokens. Waits for 'confirmed' before designing.
One skill from claude2figma.
shell
$ npx -y skills add senlindesign/claude2figma --skill reference-interpreter --agent claude-codeInstalls just this skill. Get the whole plugin for auto-invocation.
How it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/reference-interpreter
Context preview
The summary Claude sees to decide when to auto-load this skill.
Triggers when user shares a screenshot, image, URL, or design description โ or says 'analyze this', 'make a brief', 'interpret this reference'. Outputs a structured Design Brief mapping visual intent to design system tokens. Waits for 'confirmed' before designing.
Stats
Stars178
Forks16
LicenseMIT
SKILL.md
reference-interpreter.SKILL.md
--- name: reference-interpreter description: "Triggers when user shares a screenshot, image, URL, or design description โ or says 'analyze this', 'make a brief', 'interpret this reference'. Outputs a structured Design Brief mapping visual intent to design system tokens. Waits for 'confirmed' before designing." disable-model-invocation: false --- # Reference Interpreter Analyze a reference (screenshot, URL, or description) and produce a **Design Brief** that maps visual observations to design system tokens. Output the Brief, then **stop and wait for user confirmation** before building anything. Prerequisite: `figma-preflight` should have run so the Token Map and Style Registry are available. --- ## Phase 1 โ Analyze Examine the reference across these dimensions: 1. **Layout** โ structure, columns, section heights, grid width, alignment 2. **Typography** โ heading/body hierarchy, weight contrast, tracking 3. **Color** โ dark/light sections, accent usage, neutral dominance 4. **Spacing** โ generous vs compact, section padding, internal gap 5. **Visual Anchor** โ what draws the eye: large type, hero image, illustration 6. **Components** โ what UI elements are visible: cards, buttons, forms, nav --- ## Phase 2 โ Map to Design System
