agentleFS
gooseworks-aigooseworks-ai/goose-skills/skills/marketing/make-static-ads-copy-variants/SKILL.md

make-static-ads-copy-variants

Skill1.3k starsChanged 22 days agoMITView on GitHub

Step of the make-static-ads playbook: after an image is approved, makes more versions of the same picture with different hooks, headlines or fonts by a quoted re-render with the approved render attached as the brand's own image, so copy can be tested without new visuals. Offered, never default. Run make-static-ads instead; not for direct use.

1 other project uses a version of this.

Trending

More talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 1 mentionJun 2026: 0 mentionsJul 2026: 2 mentionsAug 2026: 1 mentionSep 2026: 0 mentionsOct 2026: 15 mentionsNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the gooseworks-ai/goose-skills repository that our weekly crawl found. There is no adoption data for this file yet.

Most recently taken up by

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

The biggest 5 of 20 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 20

Talked about on GitHub (20 times).

On GitHub · 20

15 more on GitHub

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:

    No new board: the parent ad's row is the basis, linked in the batch file.

    line 12

≈ “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

copy-variants

When to offer: as a hook test on a winner — after the review (Step 8), for the one or two images the marketer likes most, or later on an ad with results, or when the marketer asks "same image, different text" or "try another font". Say plainly: these test copy, not concepts — Meta treats the same picture with new words as nearly the same ad, so they go in the same ad (as extra text options), never as new concepts.

No new board: the parent ad's row is the basis, linked in the batch file. Every new line goes through the claims check before its quote.

Reads: the approved render (gooseworks:ads_creative_read creative_id, include: ["renders"]); the ad's spare hooks from the make-static-ads-ad-copy skill; the parent ad's board row and prompt; ../make-static-ads/references/fonts-and-color.md; ../make-static-ads/references/prompts.md. Writes: variant renders, each with its text and font in the batch file under the parent ad.

  1. Pick the variants: 2–4 hook directions from the parent's spare hooks for the same reason to buy (different hook formulas); optionally 2–3 font treatments from fonts-and-color.md, in the brand's colours. A new font goes into the prompt's typography line.
  2. Write each variant's prompt with the make-static-ads-compose skill (../make-static-ads-compose/SKILL.md). Images in order: the product photo first, then the parent's raw render without the logo ("Image 2 is our approved ad: keep its scene exactly; change only the words in <slot> to …"). Then gooseworks:ads_render dry_run: true, the quote as given, the marketer's yes, submit. The picture may shift slightly. The layer split (ads_creative_layerize) is not used: it returns no price before it charges.
  3. Check each variant: Pass A and B of the make-static-ads-claims-extract skill (../make-static-ads-claims-extract/SKILL.md); then the make-static-ads-render-review skill (../make-static-ads-render-review/SKILL.md): the logo placed again, the judge with rubric checks 2, 8, 11, 15 and 23, you with 1 and 12 (its step 3), one retry inside the yes.
  4. Hand over each variant under its parent ad: the image, its text, its font. Suggest running them as text options inside one flexible ad, not as separate concepts.

Done: each variant is rendered, judged and filed under its parent with its text and font.

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.