agentleFS
empowerment-aiempowerment-ai/agent-site-kit/skills/site-brief/SKILL.md

site-brief

Skill0 starsChanged 47 days agoMITView on GitHub

Interview a business owner and turn the answers into the site's content files (business.json, menu or services, page copy). Use at the start of a new site, or when the owner says "set up my website", "here's my business", or pastes notes about their business.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Gather what the owner already has: Ask them to paste anything useful: an old website URL, a Google Business profile, a menu or price list, …

    line 13
  2. Distinctive:

    Leave gaps visible: If a page needs something you don't have, stop and ask.

    line 27
  3. Very specific:

    Run npm run check, fix anything it flags, then summarize for the owner: what you filled in, what you still need from them, and the next …

    line 29

≈ “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 brief

This is the "type a prompt, get a website" moment from tools like Lovable, done properly: the agent asks for real facts first, so nothing on the site is invented.

Steps

  1. Gather what the owner already has. Ask them to paste anything useful: an old website URL, a Google Business profile, a menu or price list, an "about us" paragraph, photos. If there's an old site, read it (read-only) and pull facts from it.
  2. Ask only for what's missing, in one short list, not one question at a time:
    • Business name, phone, email, street address, and time zone
    • Hours for each day (and which days they're closed)
    • What they sell or offer, with prices if they publish them
    • Who it's for, and what makes them different, in their words
    • Two or three websites they like the feel of
  3. Write the facts into content/business.json (hours as 24-hour "HH:MM") and offerings into content/menu.json (or a services file if it's not a food business).
  4. Draft page copy in content/pages/*.md using only what the owner told you. Keep their voice: short, specific, warm. Each page needs a title (65 characters or fewer) and a description (70–165 characters) in the front matter.
  5. Leave gaps visible. If a page needs something you don't have, stop and ask. Never fill space with invented reviews, awards, years in business, or statistics.
  6. Run npm run check, fix anything it flags, then summarize for the owner: what you filled in, what you still need from them, and the next step (the build-page skill for design, or seo-research to find what customers search for).

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.