agentleFS
southleftsouthleft/figma-console-mcp-skills/skills/figma-generate-component-doc/SKILL.md

figma-generate-component-doc

Skill83 starsChanged 6 months agoMITView on GitHub

Generate complete Markdown documentation for a Figma component — anatomy/layer tree, design tokens (colors, spacing, typography), states/variants matrix, accessibility notes, content guidelines, and optional code-parity + YAML frontmatter. Use when the user wants a docs page or handoff spec for a component or component set. Triggers: 'document this component', 'generate component docs/spec', 'create a docs page for the Button', 'write up the anatomy and variants', 'component handoff doc from Figma', 'turn this component into Markdown docs'. Reads the node tree, bound variables/tokens, and designer annotations, then the agent assembles Markdown. Requires the Figma Desktop app (Plugin API).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Collect data → save JSON: Run scripts/collect-component-data.js via use_figma (skillNames: "figma-generate-component-doc").

    line 27
  2. Distinctive:

    Generate the Markdown (deterministic): Run the Node converter in a terminal:

    line 33
  3. Distinctive:

    Review & deliver: Read the emitted Markdown, sanity-check it, then write/return it.

    line 48
  4. Very specific:

    Font loading: if you add a step that writes text into Figma (e.g.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

figma-generate-component-doc — Figma component → Markdown docs

Produce a complete documentation page for one component or component set: overview, anatomy tree, design tokens, variants/states matrix, typography, accessibility, content guidelines, and (optionally) design-code parity and YAML frontmatter. This skill collects structured data from the file via use_figma, then a deterministic Node converter (scripts/generate-doc.mjs) emits the Markdown — the same collected JSON always produces identical Markdown. Do not freehand the doc from prose.

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).
  • The collect script runs anywhere (use_figma); the converter is Node and runs in a terminal (node scripts/generate-doc.mjs ...). Same split as figma-export-tokens. If you can't run Node, you can't produce the doc — say so rather than freehanding it.
  • Markdown section layout + the cleanVariantName rule → references/doc-template.md. The converter already implements every rule in that file; treat it as the spec, not a checklist for hand-assembly.
  • Reading/writing annotations as standalone specs → use the figma-annotations skill.
  • Exporting the whole token system (not just one component's tokens) → use figma-export-tokens.

Workflow

  1. Identify the target. Get the component or component-set node ID from the current selection or a URL/ID the user provides. Component sets (with variants) produce the richest docs. Set NODE_ID in the collect script. Also note the file URL (for the figma: link / frontmatter).
  2. Collect data → save JSON. Run scripts/collect-component-data.js via use_figma (skillNames: "figma-generate-component-doc"). It returns the anatomy tree, per-variant colors (with bound token id + name), typography (font family, numeric weight + name, size, line height, letter spacing), spacing tokens, component property definitions (variants/booleans/text props), the description, and annotations (with category names). Save the returned JSON to a file (e.g. collected.json).
  3. Generate the Markdown (deterministic). Run the Node converter in a terminal:
    node scripts/generate-doc.mjs collected.json [--code-info codeInfo.json] [--out docs/components/Button.md] [--frontmatter] [--file-url <figma-url>]
    It ports the source generator's section logic exactly: Overview (+ When to / When NOT to Use parsed from the description), Component Anatomy, Variants (matrix + icon mapping + configurable props), Token Specification (color + spacing tables), Typography, Content Guidelines, Accessibility, Design Annotations, and — with --code-info — Implementation, Design-Code Parity, and Changelog. cleanVariantName is applied automatically (Type=Image, Size=12 → Image / 12). Same input → identical output.
  4. Optional code parity. To add Implementation / Parity / [View Source] & [Storybook] links, read the component source and write a codeInfo.json (props, importStatement, sourceFiles, baseComponent, changelog, …), then pass --code-info codeInfo.json.
  5. Optional frontmatter. Pass --frontmatter to prepend YAML frontmatter (title, status, version, tags, figma URL, lastUpdated).
  6. Review & deliver. Read the emitted Markdown, sanity-check it, then write/return it. Report the path and a one-line summary (variant count, token count).

Notes

  • Font loading: if you add a step that writes text into Figma (e.g. stamping the doc back onto the canvas), await figma.loadFontAsync(...) first. Pure documentation generation reads only.
  • The collect script uses MAX_DEPTH to keep payloads small for deep trees — raise it only if the anatomy looks truncated.
  • Token names come from boundVariables; a color/spacing with no bound variable renders as — in the token tables (a hardcoded value to replace with a token).
  • The converter is dependency-free (Node 18+, ESM). It exits non-zero with a clear message if the JSON is missing or malformed.
  • These collect tools require the Figma Desktop app (the Plugin API isn't available in the browser).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.