DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to find what is actually broken on a screen or flow with Design How

Get a ranked review of a screen, including states a screenshot misses.

Who it is forA product designer or developer about to release a flow who wants a review of real problems, not a list of style opinions.

The problemScreenshots hide loading, error and empty states, so visual review alone misses real breakage.

The outcomeA ranked list of the issues that matter in a screen or flow, including states beyond the default view.

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

  1. Install the skills with npx skills@latest add arla6ka/design.how --skill ui-review. (inferred, check the README)
  2. Ask your agent to review the screen or flow you name.
  3. Read the ranked findings and fix the top items first.

Prompt for your agent

Using the ui-review skill from the arla6ka/design.how repo, review <target screen or flow> in this app. Expected output: a ranked list of broken items, including states a screenshot would miss. Verify that each item names a specific state or element you can reproduce.

Caveat. The README says ui-review ranks what is actually broken, but a review still depends on the screen and states your agent can reach in the app.

Share: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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