agentsclimarketplace

Setup design tokens figma

Skill southleft/skills-for-figma/skills/setup-design-tokens-figma

Open-source agent skills for the native Figma MCP server — design tokens, components, accessibility, Slides, and FigJam.

Install
npx -y skills add southleft/skills-for-figma --skill setup-design-tokens-figma

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Bootstrap a complete design-token system in Figma in one atomic step — create a variable collection, its modes (e.g. Light/Dark), and every variable with per-mode values together. Use when starting a token system from scratch: triggers 'set up design tokens in Figma', 'create a token collection with light and dark modes', 'scaffold variables', 'bootstrap a Figma theme'. Works on ANY Figma plan. For incremental edits to an existing system use manage-variables-figma; for syncing from a code tokens file use import-tokens-figma.

SKILL.md

2.9 KB, as published. Nobody here has run it

setup-design-tokens-figma — atomic token-system bootstrap

Create a variable collection + modes + all variables in a single use_figma call. This is the fastest way to stand up a new token system (or a new collection within one). Because it runs as one atomic script, either everything is created or nothing is (failed scripts apply no changes).

Skill boundaries

  • use_figma rules — load the official figma-use skill first; it is the full Figma Plugin API reference. Essentials these scripts rely on: plain JS with top-level await + return (no IIFE, no figma.closePlugin(); console.log is not returned), inputs inlined as const at the top of each script, colors in 0–1 range, load fonts before any text op, await figma.getNodeByIdAsync(...), and atomic errors (a failed script applies nothing — read the error, fix, retry).
  • Incremental CRUD / batch edits to an existing system → manage-variables-figma.
  • Sync from a code token file → import-tokens-figma.

Workflow

  1. Agree the v1 scope. List the collection name, the modes (first one is the default), and the full token set with per-mode values. Lock this before writing — it's much cheaper than editing afterward.
  2. Fill the constants in scripts/setup-tokens.js: COLLECTION_NAME, MODES, TOKENS (values keyed by mode name), and optional per-variable SCOPES.
  3. Run via use_figma (skillNames: "setup-design-tokens-figma"). It returns { collectionId, modes, created, errors }.
  4. Validate with get_variable_defs or the export-tokens-figma read script, then screenshot if you also created swatches.

Notes

  • Two-tier systems: create primitives (raw values) with this skill, then create semantic tokens that alias them using import-tokens-figma (which has the alias pass) or manage-variables-figma. Keep primitives single-mode and put theming on the semantic layer.
  • Set scopes: the default ALL_SCOPES clutters every property picker. Pass SCOPES for the surfaces each token belongs to (FRAME_FILL/SHAPE_FILL for backgrounds, TEXT_FILL for text, GAP for spacing, CORNER_RADIUS for radii, WIDTH_HEIGHT for sizing).
  • Keep one bootstrap per collection. Multiple collections = multiple runs.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.