mcpField
B
build-figma

build-figma

github.com/cursorDesign & UI14.5k99 installsUpdated today
Repository

About build-figma

An orchestration skill for turning Figma designs into production UI, intended for coding agents working in a repository. It requires the Figma plugin with connected MCP and cursor-team-kit, and uses intake and visual-verification gates before and after implementation.

Key features

  1. 01Parse Figma file and node IDs
  2. 02Collect design context and screenshots
  3. 03Map nodes to repository components
  4. 04Use the product surface's styling system
  5. 05Verify live UI against the Figma baseline
  6. 06Report evidence and remaining gaps

Use cases

  1. 01Implementing a Figma design in an existing repository
  2. 02Checking design tokens and component matches
  3. 03Comparing a live UI capture with a Figma screenshot
  4. 04Tracking visual-verification blockers

MCP support

Requires the Figma plugin and connected MCP to retrieve design context, screenshots, and asset URLs. It uses these inputs to guide production UI implementation.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cursor/plugins --skill build-figma

After installing, type/build-figmain Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
design-system-discovery.md
failure-lessons.md
visual-judge.md

Details

From the project README

Build Figma

Orchestrator for Figma → production UI. It does not replace the skills below. Read each when that phase starts; do not restate them here.

Requires figma (plugin and connected MCP) and cursor-team-kit. Check first with ../dyl-mode/references/requirements.md. Missing → stop and tell the user to run /add-plugin <name>.

Failure modes that shaped the gates: references/failure-lessons.md.

Delegate to (do not copy)

PhaseRead
Figma MCP mechanicsfigma-design-to-code from the Figma plugin, before every get_design_context
Design-system inventoryreferences/design-system-discovery.md, then any repo-local design-system skill or rule it finds
Visual claim / verdict shapeverify-this from cursor-team-kit + references/visual-judge.md
Drive live UIcontrol-ui from cursor-team-kit, or the repo's own control skill for that surface

Gates

Build-figma progress:
- [ ] 0. Parse fileKey + nodeId (refuse file-only URLs)
- [ ] 1. Intake done before any product UI edit (see below)
- [ ] 2. Mapped to the repo's primitives/tokens only
- [ ] 3. Styling in the surface's own styling system
- [ ] 4. Visual judge VERIFIED per visual-judge.md (verify-this claim shape)

Gate 1 blocks coding. "Functional first, polish visuals later" is the main failure mode.

Workflow (thin)

0. Parse URL

figma.com/design/:fileKey/...?node-id=1-2 → fileKey, nodeId (1-2 → 1:2). Branch URLs use branchKey as fileKey. No node-id → stop.

1. Intake (blocking)

Follow figma-design-to-code. Call get_design_context and get_screenshot. If the response is sparse or too large, split to implementable child nodes. Download brand assets from MCP URLs; never redraw logos.

Run design-system discovery. Then write /tmp/build-figma/<slug>/intake.md:

  • Target surface, code path, and how you will drive it live.
  • Node tree.
  • Metric table. Figma px → token, or pinned value when no token matches.
  • Node → primitive map. Each Figma node to an existing component. Mark any node with no match as new, with why.
2. Implement

Use the surface's styling system and the mapped components. When Figma px disagree with a primitive's default size, pin the Figma metric in that styling system. Do not bend the primitive's defaults globally. Hard bans below.

3. Visual judge (blocking)

Specialize verify-this with references/visual-judge.md. Treat the Figma shot as baseline and the live capture as treatment. Match theme polarity first, then apply the rubric and write the verdict. After NOT VERIFIED, fix the failed rows, recapture, and apply the rubric again. Repeat until VERIFIED or INCONCLUSIVE. Stop and report the blocker after INCONCLUSIVE; do not claim Gate 4 complete.

4. Report

Intake path, map highlights, verdict + evidence paths, remaining gaps.

Hard bans

  1. Paste Figma MCP Tailwind/React as product code.
  2. Invent brand assets when Figma or the repo has them.
  3. "Close enough" primitive for a distinct Figma structure.
  4. Trust text/button/dialog size tokens without checking Figma px.
  5. Claim visual done without the judge.
  6. Edit product UI before intake.md exists.

Comments

Markdown supported