Agent skill

Design Data

by adobe in adobe/spectrum-design-data

Look up Spectrum design tokens, component schemas, and design-system decisions when building with or extending Adobe Spectrum.

Apache-2.0Auto-check passedFrontend & Design

Install Design Data

skills CLI
$ npx skills add adobe/spectrum-design-data --skill design-data -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install adobe/spectrum-design-data design-data --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/adobe/spectrum-design-data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tools/design-data-skill/skills/design-data .claude/skills/design-data && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
design-data
GitHub stars
155
Token cost
~1.2k tokens
SKILL.md length
415 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Look up Spectrum design tokens, component schemas, and design-system decisions when building with or extending Adobe Spectrum.

  • Works in 5 steps: Start with design-data-primer to… → Use design-data-query when you know the… → Use design-data-suggest when the user… → …
  • The user asks about token values
  • SKILL.md covers Bootstrap, Tools, Workflow and When working in Cursor, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design Data is an agent skill from adobe/spectrum-design-data. Look up Spectrum design tokens, component schemas, and design-system decisions when building with or extending Adobe Spectrum. Use when the user asks about token values, component options, naming conventions, or wants to validate/explore design-token data. Also triggers when a .design-data.toml config is involved or the user mentions the design-data CLI.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Design tokens and Design systems. It works with Model Context Protocol. The repository describes itself as: Design data, including design tokens, component schemas, and tooling for Spectrum, Adobe's design system. The licence is Apache-2.0.

When your agent uses it

  • The user asks about token values
  • Component options
  • Naming conventions
  • Wants to validate/explore design-token data

Example prompts

  • “/design-data”

Requirements

  • Pre-approved tools (allowed-tools): mcp__design-data__design-data-primer, mcp__design-data__design-data-query, mcp__design-data__design-data-suggest, mcp__design-data__design-data-component, mcp__design-data__design-data-resolve

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Start with design-data-primer to understand what data is available.
  2. Use design-data-query when you know the component/property/state.
  3. Use design-data-suggest when the user describes an intent in natural language.
  4. Use design-data-component to check all available options for a specific component.
  5. Use design-data-resolve to get the concrete value for a token in a given context.

What it can do on your machine

Read from SKILL.md and the folder at commit dc75d47. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • mcp__design-data__design-data-primer
    • mcp__design-data__design-data-query
    • mcp__design-data__design-data-suggest
    • mcp__design-data__design-data-component
    • mcp__design-data__design-data-resolve

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json and toml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Design Data loads about 1.2k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 415 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from adobe/spectrum-design-data at commit dc75d47, republished under its Apache-2.0 licence (© adobe). 415 words, ~1,199 tokens.

Download SKILL.mdSave it as .claude/skills/design-data/SKILL.md (or your agent's skills folder).
name
design-data
description
Look up Spectrum design tokens, component schemas, and design-system decisions when building with or extending Adobe Spectrum. Use when the user asks about token values, component options, naming conventions, or wants to validate/explore design-token data. Also triggers when a .design-data.toml config is involved or the user mentions the design-data CLI.
allowed-tools
mcp__design-data__design-data-primer, mcp__design-data__design-data-query, mcp__design-data__design-data-suggest, mcp__design-data__design-data-component, mcp__design-data__design-data-resolve
metadata.author
adobe
metadata.version
1.3.1
metadata.designDataVersion
3.4.0
when_to_use
Trigger on: token names (color, spacing, typography, dimension), "which token", "Spectrum component options", validate tokens, design-data primer, query…

Spectrum Design Data

Access Spectrum design tokens, component schemas, and design-system structure via the @adobe/design-data-mcp MCP server (in-process wasm — no CLI binary required).

Bootstrap

Add @adobe/design-data-mcp to your project's .cursor/mcp.json (or equivalent MCP config) to activate the tools:

json
{
  "mcpServers": {
    "design-data": {
      "command": "npx",
      "args": ["-y", "@adobe/design-data-mcp"]
    }
  }
}

The server uses an embedded Spectrum snapshot — no environment variables or dataset path configuration required for read operations.

Tools

design-data-primer

Get a structural overview of the embedded Spectrum dataset: token count, available mode-sets (color-scheme, scale, contrast), component list, taxonomy fields, and data provenance. Call this at the start of a design-token session.

No required inputs.

design-data-query

Filter Spectrum tokens by a query expression. Returns an array of matching token objects.

Required input: filter (string)

Expression syntax examples:

  • "component=button" — all button tokens
  • "component=button,state=hover" — button hover tokens
  • "property=color-*" — all color property tokens
  • "colorScheme=dark" — dark-scheme tokens

Returns an empty array when no tokens match.

design-data-suggest

Suggest Spectrum tokens matching a natural-language intent using keyword-overlap scoring. Returns matches ranked by confidence.

Required input: intent (string) — e.g. "primary CTA button background color" Optional input: limit (number, default 5)

design-data-component

Get the full component declaration for a Spectrum component by ID. Returns the component's displayName, description, and all available options (variants, sizes, states, boolean props, etc.).

Required input: id (string) — kebab-case component ID, e.g. button, action-button

Call design-data-primer first to see available component IDs.

design-data-resolve

Resolve the concrete value of a Spectrum token property for a given mode-set context. Returns the winning token with its resolved value.

Required input: property (string) — token property name, e.g. background-color-default Optional inputs: colorScheme ("light" or "dark"), scale ("desktop" or "mobile"), contrast ("regular" or "high")

Show full SKILL.md (153 more words)Show less

Workflow

  1. Start with design-data-primer to understand what data is available.
  2. Use design-data-query when you know the component/property/state.
  3. Use design-data-suggest when the user describes an intent in natural language.
  4. Use design-data-component to check all available options for a specific component.
  5. Use design-data-resolve to get the concrete value for a token in a given context.

When working in Cursor

Install this skill as a Remote Rule (GitHub) — same pattern as the s2-docs skill:

Cursor Settings → Rules → Add Rule → Remote Rule (GitHub) → paste:

https://github.com/adobe/spectrum-design-data/tree/main/tools/design-data-skill/skills/design-data

For always-available tool access (higher context cost), add the MCP server to .cursor/mcp.json as shown in the Bootstrap section above.

For custom datasets with validate/diff/write, use the design-data-agent skill or @adobe/design-data-agent-mcp instead — see tools/design-data-agent-mcp/skills/design-data/SKILL.md.

Using a custom dataset

To point at a specific Spectrum version or a custom design-data fork, add a .design-data.toml to your project root:

toml
[source]
type = "github"
repo = "adobe/spectrum-design-data"
tag = "@adobe/spectrum-tokens@14.11.0"

Without a config file, the embedded Spectrum snapshot is used automatically.

© adobe, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in tools/design-data-skill/skills/design-data of adobe/spectrum-design-data.

Open the folder on GitHubat commit dc75d47

Compare with similar skills

Design Data next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Design Data compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design Data this skilladobe/spectrum-design-data155—~1.2kAutomated safety check: PassApache-2.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Figma Screen Generatorwarpdotdev/warp65k2 repos~5kAutomated safety check: PassAGPL-3.0
Extract Design Systemarvindrk/extract-design-system2361 repos~514Automated safety check: PassMIT
Website Design Taste Extractorsenlindesign/taste-skill381—~5.3kAutomated safety check: PassNone
Montage Reactwanteddev/montage-web117—~3.4kAutomated safety check: PassMIT

Similar skills

  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Figma Screen Generator

    warpdotdev/warp

    Builds or updates full Figma screens from code or a description by reusing the file's published design system components, variables and styles.

    65k GitHub starsUsed in 2 repos~5k tokens
    Frontend & DesignAuto-check passed
  • Extract Design System

    arvindrk/extract-design-system

    Extract design primitives from a public website and generate starter token files for your project.

    236 GitHub starsUsed in 1 repo~514 tokens
    Frontend & DesignAuto-check passed
  • Website Design Taste Extractor

    senlindesign/taste-skill

    Reverse-engineers a website's design from its URL into a Markdown and JSON pair holding concrete tokens and the trade-offs behind the look.

    381 GitHub stars~5.3k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • Montage React

    wanteddev/montage-web

    Guide for building UI with Montage (Wanted Design System) in React/Next.js projects.

    117 GitHub stars~3.4k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Figma Design Inspector

    asgeirtj/system_prompts_leaks

    Inspects Figma designs through the figma CLI and Figma's MCP server to read variants, spacing, tokens and layouts and to extract assets for implementation.

    69k GitHub stars~936 tokensUpdated today
    Frontend & DesignAuto-check passed

More from adobe/spectrum-design-data

  • S2 Docs

    adobe/spectrum-design-data

    Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components.

    155 GitHub stars~868 tokensUpdated 5 days ago
    Auto-check passed
  • Design Data Agent

    adobe/spectrum-design-data

    Validate, query, resolve, diff, and author spec-conformant design tokens and components using the design-data MCP tools against a local dataset.

    155 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • Enhance Sync PR

    adobe/spectrum-design-data

    Enhances auto-generated spectrum-design-data PRs from spectrum-tokens-studio-data sync (branch tokens-sync/patch-spectrum2-from-main, author mrcjhicks).

    155 GitHub stars~2.3k tokensUpdated 5 days ago
    Auto-check passed
  • Docs Voice Tone

    adobe/spectrum-design-data

    Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings.

    155 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed

Questions about Design Data

What does Design Data do?

Look up Spectrum design tokens, component schemas, and design-system decisions when building with or extending Adobe Spectrum. Design Data is an agent skill from adobe/spectrum-design-data. Look up Spectrum design tokens, component schemas, and design-system decisions when building with or extending Adobe Spectrum.

When should I use Design Data?

Design Data fits situations like: the user asks about token values; component options; naming conventions; wants to validate/explore design-token data.

How do I install Design Data in Claude Code?

Run `npx skills add adobe/spectrum-design-data --skill design-data -a claude-code`. Or copy the skill folder (tools/design-data-skill/skills/design-data in adobe/spectrum-design-data) into .claude/skills/design-data in your project. Claude Code loads it when a task matches its description.

How do I install Design Data in Codex?

Run `npx skills add adobe/spectrum-design-data --skill design-data -a codex`. Or copy the skill folder (tools/design-data-skill/skills/design-data in adobe/spectrum-design-data) into .agents/skills/design-data in your project. Codex loads it when a task matches its description.

Can I use Design Data in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adobe/spectrum-design-data --skill design-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-data, .gemini/skills/design-data, .github/skills/design-data and .opencode/skills/design-data in your project.

What does Design Data need to run?

SKILL.md names no scripts, command-line tools or credentials: Design Data is instructions for the agent only. Its frontmatter pre-approves these tools: mcp__design-data__design-data-primer, mcp__design-data__design-data-query, mcp__design-data__design-data-suggest, mcp__design-data__design-data-component, mcp__design-data__design-data-resolve.

Does Design Data access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Design Data safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Design Data use?

Design Data is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Design Data use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Design Data?

Skills that share tags, products or a category with Design Data: Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), Figma Screen Generator (warpdotdev/warp, 65k stars), Extract Design System (arvindrk/extract-design-system, 236 stars) and Website Design Taste Extractor (senlindesign/taste-skill, 381 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design Data?

adobe (a GitHub organization) maintains it in adobe/spectrum-design-data, which has 155 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 2, 2026.

Source: adobe/spectrum-design-data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.