agentleFS
feimacodefeimacode/open-design-agent-kit/.agents/skills/open-design-design-system-from-url/SKILL.md

open-design-design-system-from-url

Skill678 starsChanged yesterdayMITView on GitHub

Make a design system from a website — measure its real colours, fonts, spacing and button states in a browser, write DESIGN.md and tokens.css that agree, and check the result side by side with the site before saving — use whenever the user wants a design system, brand kit, theme or tokens taken from a website or URL ("make a design system from stripe.com", "match our site's look", "extract the brand from this page"), even if they don't mention Open Design

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 4 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the user's own words. If they say "artifact", "design tokens" or give a file path, use those terms back.

    line 13
  2. Very specific:

    Keep the machinery out of replies: no tool names, no ids like od:prototype:poster-hero, no internal files (.artifact.json, .comments.json, …

    line 14
  3. Distinctive:

    Light, dark or both: Default to light if the user doesn't care.

    line 36
  4. Distinctive:

    If the request already answers all three ("make a dark design system from https://example.com, it's our brand"), ask nothing and go …

    line 39
  5. Very specific:

    Call extract_open_design_design_system with url, extraUrls if there are any, and theme.

    line 43
  6. Distinctive:

    If the user asked for dark and the result notes that no dark theme was found, say so.

    line 50
  7. Very specific:

    Call create_open_design_design_system with a name (for a reference site, "<Name>-inspired") and a brief describing the site in a sentence.

    line 54
  8. Very specific:

    Write DESIGN.md at suggestedEntryPath and tokens.css beside it, both from the same draft:

    line 56
  9. Very specific:

    Sanity-check each role against the screenshot first: If a measured value plainly can't be that role (text that would be unreadable on --bg, …

    line 59
  10. Very specific:

    Write a review page next to the design system as review.html, and register it with register_open_design_artifact.

    line 65
  11. Very specific:

    Call check_open_design_artifact on it.

    line 70
  12. Very specific:

    Call set_active_design_system with the returned id if the user wants to design with it now (offer it).

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
<!-- generated:open-design-agent-kit -->

Make an Open Design design system from a website: measure the rendered site, write DESIGN.md and tokens.css from one set of measurements, and check the result against the site before saving it.

Request: the rest of the user's message (if there is none, ask the user: "Which website should the design system come from?")

How to talk to the user. Many people using Open Design don't write code, so:

  • Use the user's own words. If they say "artifact", "design tokens" or give a file path, use those terms back; otherwise use the plain words below.
  • Keep the machinery out of replies: no tool names, no ids like od:prototype:poster-hero, no internal files (.artifact.json, .comments.json, config.json), and not the words "register", "manifest", "sidecar", "entry" or "surface", unless the user used them first.
  • Explain a print term the first time it comes up, in one short clause, and not again.
  • Say where a file is the way the user would find it ("in your Open Design folder, under seed-swap-flyer"). Give a raw path only where the user can click it (Claude Code, Claude Desktop's Code tab, VS Code) or asks for it.
  • End each reply that finishes a step with one line on what they can do next, with at most two options ("Want it in Instagram sizes too, or is it ready to print?").
Instead ofSay
artifact, entry, registeredyour design, saved
design system, active design systemyour style (the first time: "a saved style: colours, fonts and spacing")
surface, skill, template, recipekind of design, starting layout, or nothing
workspace, output directoryyour folder, your Open Design folder
bleedprint edge ("a few millimetres extra that the printer trims off")
trim sizefinal size
preflight findings, errors"I checked it and fixed…", "one thing to look at:"
exportsave as PDF, save as an image
inline preview, MCP Appthe preview above

1. Ask only what's missing

Three things decide the run. Take each from the request when it says so, and ask only about the ones it leaves open, in one message:

  1. The address (and, optionally, up to 3 more pages on the same site, such as a pricing or product page).
  2. Light, dark or both. Default to light if the user doesn't care.
  3. Their own brand, or a reference? For a reference site the design system is named "<Name>-inspired" and no logos or images are copied.

If the request already answers all three ("make a dark design system from https://example.com, it's our brand"), ask nothing and go straight on.

2. Measure the site

Call extract_open_design_design_system with url, extraUrls if there are any, and theme.

  • ok: you get a draft (contract tokens, a [data-theme="dark"] set only if the site has a dark theme), sources saying which element each value came from, the unmeasured tokens, and the screenshot. Look at the screenshot and the role crops in the evidence bundle before writing anything.
  • partial (no browser installed): only candidate colours and fonts from the page source. Tell the user, show the candidates, and ask them to confirm the brand colour and font, or to install Chrome for a full measurement.
  • blocked: show the user the screenshot and the reason. Ask for the site's CSS, a screenshot of the page they mean, or another public page. Don't retry the same page.
  • An invalid-args error (a private address, an extra page on another site): tell the user what was refused and why.

If the user asked for dark and the result notes that no dark theme was found, say so. Don't invent dark values.

3. Write both files from the draft

Call create_open_design_design_system with a name (for a reference site, "<Name>-inspired") and a brief describing the site in a sentence. Don't pass sourceUrl: you have better measurements already. It returns the suggestedEntryPath, the id and the token contract.

Write DESIGN.md at suggestedEntryPath and tokens.css beside it, both from the same draft:

  • tokens.css: start from draftCss. Keep every measured value exactly as measured. For an unmeasured token, leave it out so the contract fallback applies, or derive it from measured ones (a color-mix() of --accent for a missing hover); never make one up, and don't fill two steps with the same value.
  • Sanity-check each role against the screenshot first. If a measured value plainly can't be that role (text that would be unreadable on --bg, a hairline as a spacing step), drop it and say so; don't write prose to explain it away.
  • DESIGN.md: the values it names (primary colour, surface, text, the font families, the type scale) must be the same values as tokens.css. Write the prose (atmosphere, layout, components, voice, do and don't) from the screenshots. For a reference site, say near the top that it is inspired by the site and name it.
  • Marks: for the user's own brand, copy the files in the result's marks into an assets/ folder beside DESIGN.md and mention them there. For a reference site, copy none.

4. Review it side by side

Write a review page next to the design system as review.html, and register it with register_open_design_artifact. One page, two columns:

  • Left, "The site": the desktop screenshot from the evidence bundle (an <img> with a relative path to it), cropped with object-fit: cover to the top 900px.
  • Right, "The design system": a sample page that uses only the new tokens.css (<link rel="stylesheet"> to it, or its :root block inlined): a hero with a heading and a primary and secondary button, a card with text, and a form row with a label, an input and a button.

Call check_open_design_artifact on it. Compare the two columns yourself (colours, font, button shape, density), fix anything that's clearly off, then show the user the review and ask whether it matches.

Apply what the user says ("the buttons are rounder on the site" → raise the radius tokens) in both files, rebuild the review and check again. Stop after two rounds of fixes: save then, and list anything still open.

5. Save

Call set_active_design_system with the returned id if the user wants to design with it now (offer it). Tell the user the design system's id and where its files are, and that the measurements are kept in the evidence bundle.

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.