agentleFS
athina-aiathina-ai/goose-skills/skills/marketing/make-static-ads-ad-copy/SKILL.md

make-static-ads-ad-copy

Skill1.3k starsChanged 22 days agoMITView on GitHub

Step of make-static-ads: writes the text for each slot the ad's template sets, then the primary texts, headline, description and CTA around the image, from usable facts and customer words. Run make-static-ads instead; not for direct use.

1 other project uses a version of this.

Trending

Quiet since March.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 1 mentionApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the athina-ai/goose-skills repository that our weekly crawl found: only 1 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Most recently taken up by

Who's talking about athina-ai/goose-skills

The biggest 1 of 1 mention linking to the repository that our crawl found. Each line is their own headline.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Done: every slot has its final words and a runner-up note.

    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

ad-copy

Reads: each board.md row (with its level and template), profile.md (how the brand writes), customer words, the claims on file, brand voice and rules. Writes: final on-image copy into the board; the surrounding copy into the batch file.

1. On-image copy

  • Format first. The on-image text fills the slots its source sets (../make-static-ads/references/levels.md): the template's text slots at close and balanced, the brand's own ad style at bold. Match slot count, length, case and voice.
  • Headline: names the relationship in the picture, in words this brand would use ("Mum has notes."). Not the feature, not the effect. Up to about eight words, two lines on a phone.
  • Write 3 candidates per ad, from different formulas: a situation call-out, a contrarian opinion with proof, a specific number, the buyer's own question answered with a usable fact, customer words (attributed), old worry vs now, a founder line, an instruction. Keep the one that makes the picture land fastest; say in one line what the runner-up loses. Keep the spares for copy variants. Never a question about the viewer's personal traits (Meta).
  • Other slots (support line, list items, label, button): only if the source has them, in short words. A factual line must be a usable fact worded as recorded (../make-static-ads/references/claims-and-policy.md §2). A fact with no slot goes in the primary text.
  • No footer brand name: the brand name is never drawn as text; the placed logo carries the brand. A tagline only when the template has a slot for it and the brand has one.

2. Copy around the image

  • Primary text A (short): the hook, one supported fact, the CTA.
  • Primary text B (story): the moment in the picture, told in two to four sentences, then the product's part in it. Don't restate features at length.
  • Link headline (the platform's headline field, not the on-image headline), description, CTA, destination. CTA fits awareness ("Learn more" cold, "Shop now" warm); the destination keeps the ad's promise. Offers and prices only as ../make-static-ads/references/claims-and-policy.md §2 says.

3. Checks

Brand voice and banned words. Customer words: ../make-static-ads/references/claims-and-policy.md, Four doors, 1. A generated person is never a customer or endorser. Real reviews keep their wording and attribution, and need permission to appear as a testimonial.

A deliberately textless ad has no headline; don't invent one to fill the row.

Done: every slot has its final words and a runner-up note; primary texts A and B, link headline, description, CTA and destination are written; rubric checks 12 (no repeat of the image text), 17 (CTA fits stage) and 18 (hook is tension) pass on the copy.

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.