Who it is forA team lead with an established app who has already built or picked a design system and needs every screen moved onto it without manual restyling.
The problemRestyling dozens of screens by hand is slow, and visual regressions are easy to miss.
The outcomeAn audit of what needs to change, then a migration where each screen is compared with its before screenshot on a new run branch.
What you need first
- A coding agent that reads skills, such as Claude Code
- Node.js, since the install and scripts run through npx and node
- Your app in a git repository, since the skills commit to a run branch
- Playwright and a Chromium browser for the scripts that drive a browser
Steps
- Install the skills with
npx skills@latest add arla6ka/design.how. - Ask your agent to run migrate-design-system in audit mode first, so it writes only its own notes under
.design-system/and commits nothing. - Read the audit notes and confirm the mapping of hex codes and pixel values to tokens made by token-mapping.
- Run the full migration, then review each screen against its before screenshot on the run branch.
- Merge the run branch yourself once you accept the results.
Prompt for your agent
Using migrate-design-system from the arla6ka/design.how skills in this repo, run audit mode on <target app path> and write the results under .design-system/. Expected output: a list of screens and values to change. Verify that no commits were made in audit mode.
Caveat. Browser-driven checks need Playwright and a Chromium, so the migration will not run its screenshot comparisons without them.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page