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

make-static-ads-fix-rejected

Skill1.3k starsChanged 22 days agoMITView on GitHub

Step of the make-static-ads playbook: fixes a static image ad the platform rejected — finds the ad, maps the platform's reason to the line or element at fault, fixes copy for free or re-composes the image text on a quote, re-runs the claims and policy checks, and answers the request. A rejected video is the video playbook's job. 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

Files
SKILL.md

fix-rejected

Runs in place of the playbook's steps: no new board. The rejected ad's board row and prompt (in its batch file) are the basis; keep its idea and change only what the rule requires.

Reads: the open Fix needed: for make-static-ads line in ads/campaigns/<slug>/rotation-requests.md and the health line of ads/campaigns/<slug>/state.md (gooseworks:file_read), or, asked in chat, the ad and the platform's exact reason (ask for both if missing); the creative (gooseworks:ads_creative_read by tag, or gooseworks:ads_template_read mode: "mine"); its batch-file entry. Writes: the fix in the batch file under the ad; a Fix ready: answer under the request line (re-read the file, insert, write the whole file back with gooseworks:file_write).

  1. Find the ad and read its copy, its on-image text, its board row and its prompt.
  2. Map the reason to the exact line or element at fault (the ad-policy-check skill (../ad-policy-check/SKILL.md)).
  3. Fix it:
    • The fault is in the copy around the image → rewrite that line (the make-static-ads-ad-copy skill (../make-static-ads-ad-copy/SKILL.md)). Free.
    • The fault is in the image → rewrite its prompt with the make-static-ads-compose skill (../make-static-ads-compose/SKILL.md): the same scene with the faulty line or element changed. Images in order: the product photo first, then the rejected ad's raw render without the logo, to keep the look. Run step 4's checks on the new prompt, then gooseworks:ads_render dry_run: true, the quote as given, the marketer's yes, submit, and the make-static-ads-render-review skill (../make-static-ads-render-review/SKILL.md), which places the logo again.
    • Nothing in the ad breaks the rule → say so and suggest asking the platform for a review.
  4. Re-run both checks on the fixed copy or prompt before any quote, and on the new render after it: the make-static-ads-claims-extract skill (../make-static-ads-claims-extract/SKILL.md) and ad-policy-check.
  5. Answer Fix ready: under the request, and offer to save the lesson in the marketer's words (the save-learning skill (../save-learning/SKILL.md)).

Done: the fixed ad passed both checks, or you said why nothing in it breaks the rule; the Fix ready: line is written.

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.