What is figma-spec-sheets?

A skill that creates or refreshes component specification files in Figma, a collaborative tool for designing user interfaces.

It is for generating Figma specs from design-data sheets, creating missing files, updating stale ones, and verifying the results through the Figma connection.

It plans which specification files are missing or outdated, replaces generated content consistently, and records what was generated.

How adobe/spectrum-design-data configures Claude Code and Codex

About the project

adobe/spectrum-design-data is a monorepo containing the design tokens, component schemas, specifications, and related datasets that define Adobe's Spectrum design system; a monorepo keeps these related packages in one repository. It is for Adobe Spectrum SDK and tooling developers who need canonical design-system data and validation artifacts. The catalogue add-ons provide workflows and integrations for working with this design data.

adobe/spectrum-design-data · 157 stars · on GitHub · opensource.adobe.com

Reuse

Borrowing it

Nothing to install: this file belongs to adobe/spectrum-design-data. 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/adobe/spectrum-design-data/main/.ai/skills/figma-spec-sheets/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/adobe/spectrum-design-data

Made for: Claude Code, Codex.

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/adobe/spectrum-design-data/figma-spec-sheets/github.svg)](https://agentmods.dev/skills/adobe/spectrum-design-data/figma-spec-sheets)

Your own site

<a href="https://agentmods.dev/skills/adobe/spectrum-design-data/figma-spec-sheets"><img src="https://agentmods.dev/badge/skills/adobe/spectrum-design-data/figma-spec-sheets/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/adobe/spectrum-design-data/figma-spec-sheets"><img src="https://agentmods.dev/badge/skills/adobe/spectrum-design-data/figma-spec-sheets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 879 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	$0.00076	$0.00879
Opus 5.5	$0.00030	$0.00352
Sonnet 5.5	$0.00015	$0.00176
Haiku 4.5	$0.00008	$0.00088

Measured today against content hash 153157b6ebc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figma-spec-sheets 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 today.

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.

.ai/skills/figma-spec-sheets/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Figma spec files

Generated files are generated only: every run replaces the whole spec frame and ignores hand edits. Load the Figma figma-use skill first (skillNames: "figma-use" on every use_figma call; prefix resource: if it came from an MCP resource).

Files live in the test folder https://www.figma.com/files/1177024566520626109/folder/657068416 (project 657068416, plan organization::1177024566520626109). tools/figma-spec-plugin/figma-files.json is the registry: component to fileKey, the hash of what was last generated, and the date. It is the authoritative list of existing files. Never edit it by hand; use plan.mjs record.

Steps

Build the CLI if needed (moon run sdk:build), then plan: node tools/figma-spec-plugin/plan.mjs plan <component>... -o <dir> (or --all). <dir>/plan.json lists, per component, action (create, update or current), fileKey, fileName and the ordered payload files. Skip current.
create: figma-files.json is the authoritative list of existing files; no tool can list a Figma folder with the current token. If the registry has no entry, create the file; afterwards, a person checks the test folder for duplicates. Call create_new_file with fileName, planKey (from the plan), editorType: "design" and projectId. Use the returned file_key.
Call create_session with the fileKey, then pass its sessionId on every call.
Send each payload file's contents as code in one use_figma call, in order, one file at a time (the Figma MCP is rate limited; back off on errors). Each call returns step results; the last returns finish with blocksRendered.
Verify: blocksRendered equals the sum of blocks in <dir>/sheets/<component>.json, there is exactly one root frame named fileName on the first page, and a get_screenshot of one block looks right.
Record: node tools/figma-spec-plugin/plan.mjs record <component> --hash <hash from plan.json> [--file-key <key>]. Commit figma-files.json.

Read the full file on GitHub · 36 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.

today Changed 153157b6ebc6
2d ago First seen · 36 lines · 76 tokens per session scan A 0f2e7afa8760

Subscribe to this mod's changes

figma-spec-sheets is a skill published in the GitHub repository adobe/spectrum-design-data (157 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 879 once invoked, about $0.0003 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 2026-11-04.

Design and UX design-system design-tokens

figma-spec-sheets next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
figma-spec-sheetsadobe/spectrum-design-data	Skill	157	today	Apache-2.0	A	76	Claude Code, Codex
extract-designManavarya09/design-extract	Skill	4.8k	yesterday	MIT	A	140	Claude Code
designlang-tokensManavarya09/design-extract	Skill	4.8k	yesterday	MIT	A	30	Claude Code
ss-learnbitjaru/styleseed	Skill	1.0k	yesterday	MIT	A	73	Claude Code, Codex
omd-applykwakseongjae/oh-my-design	Skill	567	yesterday	MIT	A	129	Claude Code, Codex
design-dnazanwei/design-dna	Skill	2.1k	2mo ago	MIT	A	192	Claude Code, Codex
use-design-mdCaesiumY/ko-design-md	Skill	75	4d ago	MIT	A	193	Claude Code

spectrum-design-data: Skill for Claude Code