What is figma-to-section?

A skill for turning a live Figma design into project components. Figma is a collaborative interface-design tool; the skill fetches design details and screenshots, records node IDs, downloads assets, and maps values into the project’s styles and components.

Use it when building a page section from a Figma frame or node and when the implementation needs the design’s exact layout, text, colours, spacing, and assets.

It keeps implementation tied to the actual design data instead of an incomplete written summary or memory.

How textura-agency/ai-design-vault configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to textura-agency/ai-design-vault. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/textura-agency/ai-design-vault/main/.claude/skills/figma-to-section/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/textura-agency/ai-design-vault

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/textura-agency/ai-design-vault/figma-to-section/github.svg)](https://agentmods.dev/skills/textura-agency/ai-design-vault/figma-to-section)

Your own site

<a href="https://agentmods.dev/skills/textura-agency/ai-design-vault/figma-to-section"><img src="https://agentmods.dev/badge/skills/textura-agency/ai-design-vault/figma-to-section/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/textura-agency/ai-design-vault/figma-to-section"><img src="https://agentmods.dev/badge/skills/textura-agency/ai-design-vault/figma-to-section.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,244 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00094	$0.01244
Opus 5.5	$0.00038	$0.00498
Sonnet 5.5	$0.00019	$0.00249
Haiku 4.5	$0.00009	$0.00124

Measured 23d ago against content hash 3ef948430fa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figma-to-section scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/figma-to-section/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma → section

Build from live Figma data, never from a text description, a summary you wrote earlier, or memory. Descriptions lose exactly the values that matter.

Resolve every path in this skill from .claude/stack.json — paths.components, paths.views, paths.assets, paths.styles.

1. Extract, in this order

get_metadata — file structure, pages, top-level frames. Gives you the fileKey and the node IDs.
get_design_context on the target node — exact text, colours, typography, spacing, layout, asset URLs. This is the source of truth for values.
get_screenshot on the same node — the source of truth for layout: column count, direction, alignment, order, positioning.

Both. get_design_context will not tell you a layout reads as three columns; the screenshot will not tell you the gap is 28px.

2. Record what you fetched

Write DESIGN-MAP.md at the repo root:

**Figma file key:** `<fileKey>`
**Source URL:** <url>
**Frame width:** <px>   ← the design base width; check it against the grid/breakpoints

| Section | Node ID | View / component | Background | Notes |
|---------|---------|------------------|------------|-------|
| Hero    | `1:234` | views/home → Hero | full-bleed image | h1 lives here |

Every section needs its node ID. QA and any later pass re-fetch from these — a section without a node ID cannot be verified against its design later.

3. Assets

get_design_context returns asset URLs that expire (~7 days). Download immediately.

Save to <paths.assets>/<section>/ — one folder per section. Favicons, OG images and manifests stay at <paths.staticRoot> root.
kebab-case, prefixed by section: hero-background.webp, team-jane-doe.webp, icon-arrow.svg.
Verify each file after download: run file <path>. Figma often returns an SVG where you asked for a raster, or a PNG named .jpg. Rename to match the real type — a mismatched extension renders as a broken image.
Sanity-check size: a content photo under ~5KB is almost certainly a vector placeholder, not the intended export. Flag it; do not ship it.
Prefer .webp/.avif for photos. Use bindings.image with explicit dimensions where the stack has an image component; plain <img> with width, height and loading="lazy" where it does not.
If a download fails: use a placeholder, add a comment saying why, and tell the user immediately — never silently skip an asset.

Read the full file on GitHub · 102 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

23d ago First seen · 102 lines · 94 tokens per session scan A 3ef948430fa4

Subscribe to this mod's changes

figma-to-section is a skill published in the GitHub repository textura-agency/ai-design-vault (25 stars, last pushed 2mo ago), licensed Unlicense. It adds 94 tokens to every session and 1,244 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.

Design and UX Frontend

figma-to-section next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
figma-to-sectiontextura-agency/ai-design-vault	Skill	25	2mo ago	Unlicense	A	94	Claude Code
webgl-holographic-foilnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	41	Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	53	Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	78	Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codex	Skill	34k	3d ago	MIT	A	52	Codex
glance-canonical-layoutsandroid/skills	Skill	10k	yesterday	Apache-2.0	A	56	Claude Code
accessibilitymicrosoft/hve-core	Skill	1.6k	yesterday	MIT	A	47	Claude Code

ai-design-vault: Skill for Claude Code