capabilities

Verify Product Image

QC gate for a generated static ad image — verify the file opens, matches the requested dimensions, shows the correct product/subject (right shape, colour, label, logo), and has no garbled text or severe artifacts. Records pass/fail/needs-human in verification.md. Used as the final check in the static ad remix flow before shipping.

by Athina AI

Run in Gooseworks View skill in Github

Install

Terminal

npx gooseworks install --claude

# Then in your agent:
/gooseworks <prompt> --skill verify-product-image

About This Skill

verify-product-image

Verify image files open, match requested dimensions, show the requested subject/product, and have no severe artifacts.

Checks

Confirm required input files exist.
Confirm output files or written plans match the skill contract.
Product/asset: the featured hero is the brand's real product (or app UI for SaaS), matching the kit asset — not a mascot, logo, or placeholder standing in for the product.
Brand alignment: colours come from the intended source (the reference's palette for style_source: template, the kit's documented colors for brand) — no invented/off-brand colour (e.g. an accent pulled off a logo or mascot). Typography matches the kit's fonts.
Text/logo: copy and label text are real and correctly spelled; any logo is the brand's correct, undistorted mark.
Record pass, fail, skipped, blocked, or needs human review in verification.md.

What's included

Confirm required input files exist.

Confirm output files or written plans match the skill contract.

Product/asset:* the featured hero is the brand's real product (or app UI for SaaS), matching the

Brand alignment:* colours come from the intended source (the reference's palette for

Text/logo:* copy and label text are real and correctly spelled; any logo is the brand's correct,

Remix Graphic Ad From Reference

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.

composites

Extract Source Sample

Given the path to a finished content-goose ad-run folder, extract everything that defines that ad — recipe shot list, VO script, characters, voices, world, atom-skills, master mp4 — and emit a `source-sample.json` in the exact shape the `upload-ad-sample` skill writes to the Goose Ads library. Also links every character and voice to the central character library at `/Users/akhil/projects/content-goose/assets/character-library/`, and if a character isn't in the library yet, adds it first then links. Use when the user wants to remix one of their existing ads — this skill produces the source JSON that the script-rewriting step and `remix-ad` consume.