design-tokens-emit
Skill10 starsChanged 28 days agoMITView on GitHub
Convert a design system spec into code-deliverable token files — CSS variables, a Tailwind config fragment, SCSS variables, or Style-Dictionary JSON. Trigger when the user says "emit tokens", "tailwind config", "css variables", "style dictionary", "convert design system to code", or wants to bridge from spec to implementation.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- blast-promptSkill
- client-outreachSkill
- content-draftSkill
- copywritingSkill
- csv-to-reportSkill
- design-accessibilitySkill
- design-buildSkill
- design-croSkill
- design-dimensionsSkill
- design-motionSkill
- design-researchSkill
- design-system-genSkill
- design-system-persistSkill
- design-visual-qaSkill
- html-extractSkill
- parallel-buildSkill
- portable-html-portSkill
- qa-gateSkill
- route-codex-reviewSkill
- route-gemini-contextSkill
- route-three-brainSkill
- seo-auditSkill
- seo-backlinksSkill
- seo-clusterSkill
- seo-competitor-pagesSkill
- seo-content-briefSkill
- seo-contentSkill
- seo-dataforseoSkill
- seo-driftSkill
- seo-ecommerceSkill
- seo-firecrawlSkill
- seo-geoSkill
- seo-googleSkill
- seo-hreflangSkill
- seo-image-auditSkill
- seo-image-genSkill
- seo-local-unifiedSkill
- seo-pageSkill
- seo-programmaticSkill
- seo-schemaSkill
- seo-sitemapSkill
- seo-strategySkill
- seo-sxoSkill
- seo-technicalSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 32
Get the design JSON: Run design-system-gen (JSON mode) or read a saved one.
- Very specific: line 41
Use --print to preview without writing.
≈ “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.
Files
design-tokens-emit
Family: design Status: Stable
Purpose
Bridge "we have a design system spec" to "we have tokens we can import." Takes a
design-system-gen result and emits real token files in the chosen format(s), so
the palette/typography/effects become part of the build instead of staying a doc.
Triggers
- "emit tokens" / "convert design system to code"
- "tailwind config" / "css variables" / "style dictionary"
- "tokens for [tailwind/css/scss]"
Inputs
- A design system as engine JSON from
design-system-gen(re-run it in JSON mode if you only have a savedMASTER.md— the emitter reads JSON, not Markdown) - Target format:
css|tailwind|scss|json|all - Output directory
Steps
- Get the design JSON. Run
design-system-gen(JSON mode) or read a saved one. - Emit tokens:
On Windows, usepython3 "${CLAUDE_PLUGIN_ROOT}/scripts/design/tokens_emit.py" --design-json ds.json --format all --out-dir tokens/pyifpython3is absent; in PowerShell the variable is$env:CLAUDE_PLUGIN_ROOT. Producestokens.css(:rootcustom properties),tailwind.tokens.js(merge intotheme.extend),_tokens.scss, andtokens.json(Style-Dictionary shape). Use--printto preview without writing. - Wire it in. Tell the user where each file goes (import the CSS, merge the
Tailwind fragment,
@usethe SCSS) and include the contrast-safeon_primarycolor for button text. - Keep it in sync. Re-run when the design system changes; tokens are generated, not hand-maintained.
Outputs
- One token file per requested format (CSS / Tailwind / SCSS / JSON)
- Wiring notes for the target stack
Dependencies
scripts/design/tokens_emit.py(required) — Python 3.10+, standard library onlydesign-system-gen(required) — upstream source of the design JSON the emitter reads
Notes
Pairs with design-build (which consumes the tokens) and design-system-persist
(which stores the source design system). SwiftUI/Compose targets are on the roadmap;
web formats ship today.
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
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.

