agentleFS
kelpi-aikelpi-ai/meta-ads-skills/skills/brand-reader/SKILL.md

brand-reader

Skill3 starsChanged 5 months agoMITView on GitHub

Read a website into a working brand kit (offer, voice, colors, fonts, proof) so ads can be written and designed without a creative brief. Use at the start of any campaign, or whenever ads keep coming out off-brand.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before writing any angles or creative.

    line 12
  2. Distinctive:

    When ads look like stock templates that could belong to anyone.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Brand Reader

Doctrine

The kickoff call an agency bills for is mostly this: reading your website carefully. An ad that does not sound and look like the brand gets scrolled past as noise, and post-Andromeda the creative itself is what the delivery system aims with. The brand kit is the input to everything downstream.

When to use

  • Before writing any angles or creative.
  • When ads look like stock templates that could belong to anyone.
  • Works with no MCP. If one is connected, the last step verifies the right Facebook Page.

Run it

Read [YOUR_WEBSITE_URL] and build me a brand kit:

1. The offer, in one sentence a stranger would understand.
2. Who it is clearly for (be specific: the customer the site is obviously written for).
3. Voice: 5 adjectives plus 3 short phrases lifted verbatim from the site that sound most like the brand.
4. Proof available: testimonials, numbers, named clients, guarantees. Quote them exactly; do not improve them.
5. Visual kit: brand colors (hex if visible in the CSS or brand pages), fonts, and how imagery is treated.
6. What the site is silent about that ads would need (price? shipping? guarantee?). List these as open questions, not guesses.

If I have a Meta Ads MCP connected, list my Facebook Pages so I can confirm which one these ads will run from.

Guardrails

  • Quote proof verbatim. Never invent a testimonial, round a number, or upgrade "customers love us" into a statistic.
  • Open questions stay open. The gaps list is the point; a guessed answer poisons every ad downstream.

Good output looks like

A one-page kit you could hand to a stranger who could then write an on-brand ad without visiting the site, plus an honest list of what is missing.

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.