agentleFS
Sign inStart free
empowerment-aiempowerment-ai/agent-site-kit/skills/build-page/SKILL.md

build-page

Skill0 starsChanged 47 days agoMITView on GitHub

Design or redesign a page (or a section of one) following DESIGN.md, then screenshot it at phone and desktop width and critique it before showing the owner. Use for "make the homepage look better", "add a section", "build the menu page", or any visual change.

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. mrdainami/3d-webpage-kit★ 4same name
    2. matthewharrilal/claude-skills★ 0same 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 repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read DESIGN.md and src/app/globals.css.

    line 10
  2. Distinctive:

    Every image needs real alt text.

    line 18
  3. Very specific:

    Start the site (npm run dev) if it isn't running.

    line 22
  4. Distinctive:

    Look at the screenshots critically, like a designer would:

    line 26
  5. Very specific:

    If you set a rule worth keeping (a new component or pattern), add it to DESIGN.md.

    line 32

≈ “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

Build a page, then check your own work

Before you start

  • Read DESIGN.md and src/app/globals.css. Use only the existing color tokens, fonts, and components. Don't add a new color or font without asking.
  • Content comes from content/. Layout code in src/ reads it; it never hard-codes facts.

Build

  1. Make the change in the smallest set of files that does the job.
  2. Mobile first: it must work at 390px wide with no sideways scrolling.
  3. Every image needs real alt text. Every button needs a clear label.

Critique (don't skip this)

  1. Start the site (npm run dev) if it isn't running.
  2. Take screenshots at 390px and 1440px wide. Use the Playwright MCP tools (browser_resize, then browser_take_screenshot with fullPage: true) if they're connected; otherwise ask the owner to check the preview.
  3. Look at the screenshots critically, like a designer would:
    • Does anything overflow, overlap, or look cramped at 390px?
    • Is there one clear primary action per screen?
    • Is text readable against its background (no muted text on dark panels)?
    • Does it still look like the rest of the site (DESIGN.md)?
  4. Fix what you find, screenshot again, and only then show the owner.
  5. If you set a rule worth keeping (a new component or pattern), add it to DESIGN.md.

Finish with npm run check and npm run build, then summarize the change in plain English.

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