AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

jury — Awwwards-style Website Scoring

Scores a live URL or local production build exactly as an Awwwards juror would — from screenshots and measured metrics only — and returns an evidence-backed score card with a ranked fix list.

Design & UIIntermediate★ 1,042⑂ 45AI score 9/10Last updated: Oct 26, 2026

What it does

  • Captures one screenshot set per page type with Playwright: desktop 1440, a throttled 390px phone (4x CPU, slow 4G), reduced motion, keyboard focus, rest/hover pairs, idle motion, page-transition frames and the 404.
  • Measures LCP, CLS, FPS, serious axe violations, overflow, SEO and metadata into audit.txt and summary.json.
  • A fresh "blind" critic subagent — which never sees the source, README or your pitch — scores Design (40%), Usability (30%), Creativity (20%), Content (10%) plus six developer areas (Semantics/SEO, Animations, Accessibility, WPO, Responsive, Markup/Meta).
  • Writes scorecard.md where every number cites a screenshot file or report field, followed by fixes sorted by score impact.
  • Applies a calibration offset to estimate the Honorable Mention / Site of the Day band, always labelled as an unaffiliated estimate.

Who it's for

  • Designers and frontend devs sanity-checking a portfolio or landing page before submitting to Awwwards.
  • Agencies that need an evidence-based design QA report for a client.
  • Anyone comparing their site against a competitor on identical criteria.

Examples

  1. "Score my portfolio example.com" → crawls page types, shoots, audits, then returns the card plus a ranked fix list.
  2. A Next.js repo: "review this build" → runs npm run build, serves production on port 4400, and scores that (dev servers are refused).
  3. "Mine vs theirs" → each URL gets its own fresh critic, then the two cards are shown side by side.
  4. Re-score after fixes → the old card is renamed scorecard-1.md and a brand-new critic reports the per-category delta.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/juliobsz/skills/HEAD/jury/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the jury folder from the GitHub repo juliobsz/skills into my ~/.claude/skills/jury/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/juliobsz/skills.git /tmp/juliobsz-skills && mkdir -p ~/.claude/skills && cp -r /tmp/juliobsz-skills/jury ~/.claude/skills/jury

⚠ This is a third-party skill. Check the source repository before installing.

  1. Confirm Node.js 20 or newer: node -v
  2. Clone the repo: git clone https://github.com/juliobsz/skills.git /tmp/juliobsz-skills
  3. Copy the skill into place: mkdir -p ~/.claude/skills && cp -r /tmp/juliobsz-skills/jury ~/.claude/skills/jury
  4. Install the measurement tools once into a cache folder (so no dependencies are added to someone's project): mkdir -p ~/.cache/jury && cd ~/.cache/jury && npm init -y && npm i -D playwright axe-core
  5. Install the browser engine: cd ~/.cache/jury && npx playwright install chromium
  6. Restart Claude Code and ask: "use jury to score https://example.com".
  7. Evidence lands in .jury/<host>/ in your current directory: screenshots, audit.txt and scorecard.md.
  8. Sites behind a login or password cannot be scored — have a public URL or a local production build ready.
View source on GitHub ↗License: MIT