gooseworks-ai/goose-skills / skills/shared/remix-graphic-ad-from-reference
remix-graphic-ad-from-reference
VerifiedRecreate 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.9 KB |
| assets/overlay-template.html | other | 4.8 KB |
| requirements.txt | manifest | 119 B |
| scripts/cutout_product.py | script | 2.7 KB |
| skill.meta.json | config | 445 B |
| tests/expected-output.md | markdown | 1020 B |
| tests/human-test.md | markdown | 897 B |
| tests/sample-input.md | markdown | 1019 B |
| tests/smoke-test.md | markdown | 1.0 KB |
| tests/verifier.md | markdown | 1.1 KB |
tests/sample-input.md
View on GitHub# Sample input — remix-graphic-ad-from-reference
```yaml
reference_image: ./reference-product-sky-arrows.jpg # a Pinterest pin from the ads library
product: ./brand-assets/product-hero.png # real brand product render (clean bg or transparent)
brand:
name: Example Gut Co
palette: { primary: "#1d3d39", accent: "#632240", paper: "#eee3d6" }
font: Lexend
url: examplegut.co
copy_changes:
pre: "Start feeling good,"
big: "from the gut."
callouts: ["Beats bloating", "Smoother digestion", "All-day energy"]
social_proof: "10,000+ happy customers"
discount: { top: "up to", pct: "45", sub: "your first order" }
aspect: 4:5 # -> poster canvas (1080x1350)
route_hint: auto
```
Reference anatomy (expected): sky background, product held up / floating center, 3 white curved
benefit arrows, 5 stars + social proof bottom-left, scalloped discount seal bottom-right.
Expected route: **html** (floating product on a sky gradient — default). Use **gpt_image_2** only if a real hand-holding-product photo is required.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |