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 binggandata/bggg-skills --skill ngs-amazon-image-studiogit clone --depth 1 https://github.com/binggandata/bggg-skillsWrote 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/binggandata/bggg-skills/ngs-amazon-image-studio)<a href="https://agentmods.dev/skills/binggandata/bggg-skills/ngs-amazon-image-studio"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/ngs-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/binggandata/bggg-skills/ngs-amazon-image-studio"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/ngs-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 | $0.00086 | $0.05745 |
| Opus 5.5 | $0.00034 | $0.02298 |
| Sonnet 5.5 | $0.00017 | $0.01149 |
| Haiku 4.5 | $0.00009 | $0.00575 |
Grade A, and why
ngs-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 2mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NGS Amazon Image Studio
目标
根据用户提交的产品业务卡,生成一张、多张或整套跨境电商商品图。只支持以下六类:
- 白底图
white-background - 展示图
showcase - 卖点图
selling-point - 英雄图
hero - 细节图
detail - 场景图
lifestyle
整套模式默认包含以上六类各 1 张。用户未明确要求整套时,不得自行扩充为整套。
本 Skill 不负责 A+ 页面、不上传 Amazon 或其他电商后台,也不生成独立的尺寸图、成分图、模特图、HOW TO USE 图或使用对比图。尺寸、成分、人物和使用步骤只有在用户选定的六类图片确实需要时,作为画面内容处理,不作为独立图片入口。
强制执行顺序
严格按以下顺序推进,不得一开始同时抛出业务卡、图片选择和输出路径三个问题:
产品业务卡
-> 用户选择生什么图并确认尺寸
-> 用户指定或确认输出位置
-> 建立产品事实锁与主控参考图
-> 建立统一视觉概念与创意母题
-> 输出逐图规划和文件名
-> 用户明确确认
-> 按规划逐张生图
-> 质检、保存、回报文件路径
第一步:先收产品业务卡
首次触发时,先读取并使用 references/business-card.md。
- 如果用户已经给出部分字段,整理已有信息,只追问缺失的必填项,不让用户重复填写。
- 产品图、产品名、产品品类为必填。品类用于确定事实边界和输出目录命名。
- 用户提供竞品链接、ASIN 或参考图时,按
references/competitor-benchmark.md做受控拆解,产出竞品洞察卡并入统一视觉概念。 - 用户给出存放提示词的多维表格或文档时,读取该记录中本产品对应类型的提示词字段,作为第八步的提示词来源。
- 用户未提供任何参考时,不擅自决定:在第二步询问图片类型和尺寸时,必须同时询问要不要联网找参考。用户同意后,必须联网检索同品类优秀范例(Amazon 头部套图、A+ 模块、行业案例),逐个观察展示图、卖点图、英雄图、细节图、场景图分别怎么做,提炼洞察后再做统一视觉概念;联网结果不足时直接说明,不虚构范例。用户明确说不用找参考时,按品类常识和自主创意完成概念设计,并在规划说明中讲清概念来源。
- 竞品与联网范例洞察只作用于展示图、卖点图、英雄图、细节图和场景图;白底主图不参考竞品和范例,只以产品事实和平台合规为准。
- 其他字段允许留空。先根据产品品类、产品结构和本轮目标对业务卡做针对性增删,再只追问真正影响生图的字段。
- 不得把同一张完整业务卡机械套给所有品类;护肤品、服装、电子产品、家居用品、宠物用品等应使用不同的补充字段。
- 只有当用户后来选择的图片缺少必要信息时,才按需追问。
- 此阶段只收业务卡,不询问输出路径,不开始生图。
第二步:再问用户生什么图和尺寸
业务卡的必填项齐全后,向用户说明可选的六类图片,并询问本次模式:
- 单张:只生成 1 张指定类型。
- 多张:只生成用户点名的类型和数量。
- 整套:默认六类各 1 张,但允许用户删减、增减同类数量或调整顺序。
接受自然语言,例如“做一张白底图”“卖点图和细节图各一张”“生成整套”。不要强迫用户按编号回复。
询问图片类型时必须同时提醒尺寸:
- 用户未指定时,白底图、展示图、卖点图和细节图默认生成
2000×2000 px、1:1;英雄图和场景图默认生成2000×1500 px、4:3。 - 用户可以让本轮全部图片使用同一尺寸,也可以为每张图分别指定尺寸。
- 用户只说比例但没有说像素时,先给出建议像素并请用户确认;不要静默猜测。
- 整套模式未指定尺寸时,英雄图和场景图默认
2000×1500 px、4:3,其余四类默认2000×2000 px、1:1。
使用下面的话术,不得等到生成规划阶段才第一次说明默认尺寸:
这次想生成哪种图片?可以选择白底图、展示图、卖点图、英雄图、细节图、场景图,也可以选择多张或整套。请同时告诉我需要的图片尺寸;如果不指定,英雄图和场景图默认按 2000×1500 px、4:3 生成,其余类型默认按 2000×2000 px、1:1 生成。
用户此前没有提供任何竞品链接、ASIN、参考图或个人视觉想法时,必须在同一轮追问是否需要联网找参考:
你还没有给我对标参考。要不要我联网找同品类的优秀套图做参考?需要的话我会先拆解优秀范例再设计;不需要的话我按品类经验和统一视觉概念直接设计。
What ships with it
16 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.
- references/business-card.md 6.1 KB
- references/competitor-benchmark.md 6.8 KB
- references/creative-direction.md 6.5 KB
- references/image-backends.md 2.4 KB
- references/image-types.md 1.5 KB
- references/meta-prompts/01-white-background.md 609 B
- references/meta-prompts/02-showcase.md 6.5 KB
- references/meta-prompts/03-selling-point.md 10 KB
- references/meta-prompts/04-hero.md 50 KB
- references/meta-prompts/05-detail.md 25 KB
- references/meta-prompts/06-lifestyle.md 9.6 KB
- references/output-naming.md 2.6 KB
- references/prompt-engineering.md 7.8 KB
- references/reference-image-techniques.md 4.6 KB
- scripts/generate_image.py 6.1 KB runs code
- scripts/requirements-image-api.txt 30 B
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.
- 2mo ago First seen · 242 lines · 86 tokens per session scan A f7a768d28f57
ngs-amazon-image-studio is a skill published in the GitHub repository binggandata/bggg-skills (612 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 5,745 once invoked, about $0.0003 per session on Opus 5.5. 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
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
cloudbase-wechat-integration
A guide for connecting CloudBase applications to WeChat services, including payments, official accounts, and user identity.