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

make-static-ads-compose

Skill1.3k starsChanged 20 days agoMITView on GitHub

Step of make-static-ads: writes each ad's render prompt and ordered image list from its concept-board row, one per ad and ratio, ready for a quoted render. 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

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

  • 1

    Very specific

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

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

    Shared foundation: Write it once for the batch (prompts.md §2) with the brand's look from profile.md, its fonts and rules.

    line 15
  2. Distinctive:

    Copy: Every word to be drawn is in quotes, exactly as the board has it, placed in its slot.

    line 17

≈ “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

compose

Read first: ../make-static-ads/references/prompts.md. Reads: the board.md row with its final copy, level and template; profile.md (the brand's real look); ../make-static-ads/references/levels.md; the product record and photos, the logo, the brand kit's colours and fonts, every must and dont rule. Writes: per ad and ratio, the exact prompt and image_urls into the batch file, the template it is based on as template_id (its id from ads_template_read) or, with no id, as reference_image_url (the template's public image URL), never both, so the app shows "Based on" (this only records it; the image still goes in image_urls when levels.md says so), a title ("<brand> — <headline> (<level>)"), plus a render-<ad>-<ratio>.json holding the gooseworks:ads_render arguments on a host with files.

  1. Product images. Pick the official photo(s) that show the label most clearly from the angle the scene needs; for software, real UI screenshots or the mascot, never the logo (../make-static-ads/SKILL.md, Before you start). Public https URLs only; a local or attached file goes through gooseworks:media_upload first. Look at each one before using it.
  2. Shared foundation. Write it once for the batch (prompts.md §2) with the brand's look from profile.md, its fonts and rules. Reuse it word for word.
  3. Style, layout and scene. For each ad, write prompts.md §3 from the board row: its own style, the template's layout as the level keeps it, then the scene. Leave the logo area clear (no shell and a drawn logo chosen: attach the logo instead), and attach images as prompts.md §1 says. The physical event and the protected choice go in as concrete sentences; the protected choice also appears word for word.
  4. Copy. Every word to be drawn is in quotes, exactly as the board has it, placed in its slot. Nothing else is asked to be drawn.
  5. Ratios. One prompt per ratio the placements need (prompts.md §4, ../make-static-ads/references/formats-and-placements.md).
  6. Read it back (prompts.md §5). Then hand it to the claims check.

Engine: leave engine unset (the default) unless the marketer asked for another or the default refused the content. A prompt with no attached images stays on the default engine. A changed prompt after the claims check goes through the check again.

Done: each ad and ratio has its prompt, image list and render arguments; each passed the read-back.

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.