Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zpoint/vibe-seller --skill amazon-image-studiogit clone --depth 1 https://github.com/zpoint/vibe-sellerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zpoint/vibe-seller/amazon-image-studio)<a href="https://agentmods.dev/skills/zpoint/vibe-seller/amazon-image-studio"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/amazon-image-studio/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zpoint/vibe-seller/amazon-image-studio"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/amazon-image-studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00139 | $0.01626 |
| Opus 5 | $0.00069 | $0.00813 |
| Sonnet 5 | $0.00028 | $0.00325 |
| Haiku 4.5 | $0.00014 | $0.00163 |
Grade A, and why
amazon-image-studio scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Image Studio
Amazon-specific knowledge for generating listing images with the
general vibe_seller_generate_image tool. The tool itself documents
the generic contract (user-language prompt, references carry a real
subject's appearance, roles by position, the user-confirm pause) — this
skill adds only what is Amazon:
1. Amazon image requirements
MAIN image (the one search results show — strictest):
- Pure white background, exactly RGB (255,255,255) — off-white fails Amazon's automated scan.
- Product fills ~85% of the frame, fully visible, not cropped.
- NO text, logos, badges, watermarks, borders, props, or accessories not included in the purchase. Product only, as the buyer receives it.
- ≥1000px on the longest side; ≥1600px recommended (enables zoom). Square (1:1) displays best. JPEG/PNG.
- Category variations exist (e.g. adult apparel is usually shown on a model; shoes as a single shoe at an angle). When in doubt, mirror what the store's own live listings of the same category do.
Secondary images (gallery slots 2-7+): lifestyle shots, infographics with feature callouts, dimension/scale charts and comparison tables are all allowed and convert well. On-image text is fine HERE (never on the main image) — spell every word exactly in the prompt and proofread the result character by character.
2. Collecting reference images
- Supplier page (e.g. 1688): extract the original gallery image
URLs from the page (full-size, not thumbnails) and pass them as
reference_imagesdirectly — the generator fetches URLs itself. - Amazon listing (style reference): open the listing's dp page and
take the hi-res image URLs (
m.media-amazon.com/images/I/…, request the large_SL1600_variant). These carry the store's composition, palette and infographic layout. - Never pass a blank/placeholder image. Two traps produce them:
- listings whose images were never uploaded show a "No image available" placeholder;
- lazy-loading pages serve tiny stand-in GIFs (e.g. 60×40px) until the image scrolls into view. Judge what you actually fetched — is it a full-resolution product photo? A placeholder passed "just in case" poisons the generation.
- Style-reference search order (autonomous, never stall):
- a live-imaged listing of the same product type on this store;
- otherwise ANY live-imaged listing on this store (brand style — hero look, palette, chip band — carries across categories; you reference its composition, never its product);
- if the whole store has no live images, ask the user once (AskUserQuestion): provide a style image (they can drag one into the confirmation popup's reference area) or proceed with supplier photos only — optional; proceed immediately if declined.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 113 lines · 139 tokens per session scan A 14cf8e73d710
amazon-image-studio is a skill published in the GitHub repository zpoint/vibe-seller (64 stars, last pushed yesterday), licensed Apache-2.0. It adds 139 tokens to every session and 1,626 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
beat-sync-reel
Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.
byted-livesaas-master
A control tool for managing business livestreams, including rooms, comments, viewers, product cards, coupons, and live-session settings.
byted-ind-ecom-product-video-prompt
A structured prompt-writing guide for creating e-commerce product videos with Seedance 2.0. It turns one or more product images into a product showcase script using scene settings, timed shots, and output constraints.
tiktok-shop-branding
Brand building and positioning on TikTok Shop. Brand identity development, content pillars, community engagement, brand storytelling, and authenticity strategies. Use when the user asks about TikTok branding, brand building, brand identity, or brand positioning on TikTok.
tiktok-shop-content-strategy
TikTok Shop content creation strategy and planning. Trending formats, viral hooks, product showcasing, hashtag strategy, and content calendar development. Use when the user asks about TikTok content strategy, viral content creation, TikTok marketing, or content planning.
amazon-listing-images
Amazon product listing image strategy and optimization. Comprehensive shot planning, infographic design, lifestyle photography, mobile optimization, and conversion-focused visual content. Use when the user asks about Amazon images, product photography, visual optimization, or listing conversion.