Skip to content

gooseworks-ai/goose-skills / skills/shared/remix-graphic-ad-from-reference

remix-graphic-ad-from-reference

Verified

Recreate a static graphic ad (Pinterest pin, IG/FB feed image, poster) from a reference image, swapping in a new brand's product and new copy while keeping the reference's layout, composition, and visual energy. ALWAYS generated with GPT Image 2 in edit-the-reference mode (fal-ai/gpt-image-1/edit-image, a billed FAL generation); the HTML/goose-graphics overlay is only an optional text-finishing step, never the generator. The static-graphics counterpart to the video remix-ad skill; this is what the app calls when a user picks a reference ad and wants it for their own product.

FileKindSize
SKILL.mdskill md18.9 KB
assets/overlay-template.htmlother4.8 KB
requirements.txtmanifest119 B
scripts/cutout_product.pyscript2.7 KB
skill.meta.jsonconfig445 B
tests/expected-output.mdmarkdown1020 B
tests/human-test.mdmarkdown897 B
tests/sample-input.mdmarkdown1019 B
tests/smoke-test.mdmarkdown1.0 KB
tests/verifier.mdmarkdown1.1 KB

tests/human-test.md

View on GitHub
# Human acceptance — remix-graphic-ad-from-reference

Show the reviewer the **reference** and the **remixed ad** side by side. Ask:

1. **Same ad?** Does the remix read as the same layout/composition/energy as the reference
   (not a generic redesign)? It should feel like "that ad, but for my product."
2. **Product right?** Is it the correct SKU, label legible, logo undistorted, on-brand colors?
3. **Copy right?** Headline, callouts, social proof, and **discount/price** all correct and
   correctly spelled? (Zoom to 100% — text errors hide in thumbnails.)
4. **Brand-safe?** No fear framing, no competitor jab, no unverifiable claim introduced by the swap.
5. **Editable?** If copy/price will change often, was the HTML path used (so edits don't need a re-roll)?

Reject if the layout drifted from the reference, the label is wrong, any text is misspelled, or
the discount value is off.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall