agentleFS
Sign inStart free
titouannwtttitouannwtt/claude-tools/skills/site-design/SKILL.md

site-design

Skill1 starsChanged 12 days agoMITView on GitHub

Analyze the design of an existing website (palette, typography, spacing, radii, shadows, CSS variables, breakpoints, screenshots at mobile, tablet and desktop widths) to draw inspiration from it, reproduce it or audit it. Use when the user gives a site URL and asks for its style, its colors, its fonts, to copy it in spirit, or to check its responsive rendering.

  • Reads credentials
  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. panaversity/ksor★ 225same name
    2. RichardBray/skills★ 5same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository12 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read summary.md (short). Open the screenshots with Read to judge the overall impression: the measurements say what, the screenshots say …

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

site-design

A script loads the page in Chromium (Playwright), measures the computed styles of the visible elements, and writes screenshots and a summary. Zero model tokens for the measurement; you then read summary.md and look at the screenshots.

Commands

Script: ~/.claude/skills/site-design/scripts/site_design.py. Output: JSON on stdout.

  • analyze "<url>" --out <folder>: writes shot-375.png, shot-768.png, shot-1280.png, design.json, summary.md.
  • --widths 375,1440: other widths (the largest is used for the measurements). --dark: captures and measures the largest width in dark mode (the measurements then describe the dark theme; run twice to compare).
  • doctor: checks Playwright and Chromium.

After the analysis

  1. Read summary.md (short). Open the screenshots with Read to judge the overall impression: the measurements say what, the screenshots say whether it looks good.
  2. Report in three blocks: identity (palette, fonts, tone), system (size scale, spacing, radii, shadows), responsive (horizontal scrolling, breakpoints). Cite the measured values.
  3. To reproduce a style: draw inspiration from the system (scale, rhythm, contrasts), do not copy texts, logos, images or licensed fonts.
  4. Limits: a background set only on body or html does not appear in the backgrounds; third-party stylesheets (other domain) deliver neither variables nor breakpoints; a site behind a login cannot be analyzed.

Exit codes

CodeMeaningAction
0SuccessRead summary.md and the screenshots.
4Page blocked (403, 429)Rerun once with --use-proxy; otherwise say so.
5Playwright or Chromium missingSee Installation.
7Page unreachableCheck the URL and the connection.
2Invalid URLAsk for an http(s) URL.
1Unexpected errorRepair the script (see below).

Installation

Mac: python3 -m venv ~/.venvs/site-design && ~/.venvs/site-design/bin/pip install playwright && ~/.venvs/site-design/bin/playwright install chromium (if a private pip index gets in the way, add --isolated --index-url https://pypi.org/simple). The script switches to that environment by itself. VPS: pip install --user playwright && python3 -m playwright install --with-deps chromium.

Proxy

--use-proxy: residential proxy from local.env (key IPROYAL_RESIDENTIAL_URL), only after a block. Limited budget: a page loads its images, so prefer a single pass. Never display the proxy value.

Repair

Fix <claude-tools>/skills/site-design/scripts/site_design.py, then python3 -m unittest discover -s tests in the skill's folder. Two attempts at most, then report the exact message to the user.

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.

Check your setup, free