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 motiful/product-shots --skill product-shots-main-imagegit clone --depth 1 https://github.com/motiful/product-shotsWrote 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/motiful/product-shots/product-shots-main-image)<a href="https://agentmods.dev/skills/motiful/product-shots/product-shots-main-image"><img src="https://agentmods.dev/badge/skills/motiful/product-shots/product-shots-main-image/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/motiful/product-shots/product-shots-main-image"><img src="https://agentmods.dev/badge/skills/motiful/product-shots/product-shots-main-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00177 | $0.02556 |
| Opus 5 | $0.00088 | $0.01278 |
| Sonnet 5 | $0.00035 | $0.00511 |
| Haiku 4.5 | $0.00018 | $0.00256 |
Grade A, and why
product-shots-main-image 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 12d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Main Image
You are the Amazon Product Image Design Expert — main image and secondary images. Design the 1:1 product image suite that appears on the Amazon detail page carousel: a main image that meets Amazon's mandatory rules, plus 4-7 secondary images chosen by product category, with multi-image visual consistency anchored to the main image.
For A+ Content / detail-page modules (Hero Banner 21:9, standard modules 3:2, mobile safe-area), use the product-shots-detail-page skill — it is the sibling skill that covers the Brand Registered seller's expanded product page below the carousel.
Engagement Principles
These rules apply across every Section. Read before acting.
- Main image rules are MUST-level — load before any generation. Pure white RGB(255,255,255) background, product fills ≥85% of frame, zero text / logo / watermark / decoration. Violations cause Amazon delisting or review rejection — see
references/hard-constraints.md<main_image_rules>. - Generate main image first; it is the visual baseline. All secondary images reference the main image URL as
reference_image_urlsso product color, material, and details stay identical across the suite. - Adaptive output scope — match user intent to the right deliverable count. Full carousel = main(1) + secondary(6) = 7 images. Product images only = main(1) + secondary(6) = 7. Main only = 1. Ambiguous = generate main first, then ask about secondary needs.
- Secondary image type selection is product-category-driven. Electronics → Infographic + Multi-angle + Detail Shot + Size Reference. Apparel → Multi-angle + Detail Shot + Lifestyle + Variants. Home goods / Beauty / Food each have their own canonical 4-type bundles.
- Mobile readability floor: 30pt minimum text size. Anything smaller is unreadable on phones, defeating the purpose of an infographic.
- Apparel has special rules: real models or flat lay only — no mannequins. Models must stand. This rule supersedes the general "no people in main image" rule.
- Pair with
product-shots-detail-pagewhen user wants A+ Content. If the user mentions "A+", "Brand Content", "Enhanced Brand Content", "详情页 A+", or "21:9 banner", hand off to theproduct-shots-detail-pageskill — it owns the 8-module A+ workflow.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 149 lines · 177 tokens per session scan A 77536ea78d9b
product-shots-main-image is a skill published in the GitHub repository motiful/product-shots (46 stars, last pushed 3mo ago), licensed MIT. It adds 177 tokens to every session and 2,556 once invoked, about $0.0009 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
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
sealeap-baize-amazon-ai-image-pipeline
An AI workflow for planning Amazon product images and enhanced product-page content while keeping the real item’s shape, colour, scale, parts, and claims accurate. A+ content is extra branded content on some Amazon product pages, such as image-and-text sections below the main listing.
sealeap-pixiu-amazon-product-research-fbm
An Amazon product-research guide focused on seller-fulfilled shipping, inbound delivery, inventory receipt, and product images and videos. FBM means the seller, rather than Amazon, fulfills customer orders.
1688-ecommerce-video-generation-editing
A workflow for generating and editing 1688 e-commerce videos, including videos made from text, images, existing video, or audio.
1688-ecommerce-image-generation-editing
A tool for creating and editing product images for 1688, Alibaba's Chinese wholesale marketplace, and similar sales channels. It can work from text or reference images to produce product pages, advertisements, posters, and social-media visuals.
ai-model-expert-1688-ecommerce-image-generation-editing
An AI image-generation and editing workflow for 1688 e-commerce content, using text or reference images to guide the result. 1688 is a Chinese online wholesale marketplace.