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

How to score a live website like an Awwwards jury with Skills

Get a scorecard with screenshots and measurements for any reachable site.

  • Content
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI

Who it is forA designer or developer who wants an honest, evidence-based review of a live site before showing it to a client or submitting it.

The problemOpinions about a site's design, speed and accessibility are hard to compare, and most reviews do not cite evidence.

The outcomeA .jury/ folder with a scorecard.md, screenshots and reports, where every number cites a screenshot or measurement, and fixes ranked by how much score they would gain.

What you need first

  • Node 22.20+ for the skills CLI (helper scripts need Node 20+)
  • An agent that supports skills, such as Claude Code, Codex, Cursor or Gemini CLI
  • A model that can read images, so the QA loop can check its own screenshots
  • Playwright and a Chromium browser (the skills install them when needed)
  • A Vercel, Netlify or Cloudflare account only if you want the site deployed

Steps

  1. Run npx skills add juliobsz/skills -g in a terminal.
  2. Open a new agent session so it loads the skill.
  3. Type /jury https://your-site.com with the URL of the live site.
  4. Open .jury/scorecard.md and read the ranked fix list first.
  5. Check the jury estimate band against the critic score before you act on it.

Prompt for your agent

Using the juliobsz/skills repo, run the /jury skill on <target URL>. Expect a .jury/scorecard.md file with screenshots, Core Web Vitals measurements and a ranked fix list. Verify that each score in the scorecard links to a screenshot or measurement in the .jury folder.

Caveat. The jury estimate rests on two winning sites and is not affiliated with Awwwards, and pages behind a login cannot be scored.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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