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 wubin1836/ai-ecommerce-expert-agent-skills --skill ai-ecommerce-expert-batch-video-variationsgit clone --depth 1 https://github.com/wubin1836/ai-ecommerce-expert-agent-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/wubin1836/ai-ecommerce-expert-agent-skills/ai-ecommerce-expert-batch-video-variations)<a href="https://agentmods.dev/skills/wubin1836/ai-ecommerce-expert-agent-skills/ai-ecommerce-expert-batch-video-variations"><img src="https://agentmods.dev/badge/skills/wubin1836/ai-ecommerce-expert-agent-skills/ai-ecommerce-expert-batch-video-variations/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/wubin1836/ai-ecommerce-expert-agent-skills/ai-ecommerce-expert-batch-video-variations"><img src="https://agentmods.dev/badge/skills/wubin1836/ai-ecommerce-expert-agent-skills/ai-ecommerce-expert-batch-video-variations.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 | $0.00302 | $0.03561 |
| Opus 5 | $0.00151 | $0.01781 |
| Sonnet 5 | $0.00060 | $0.00712 |
| Haiku 4.5 | $0.00030 | $0.00356 |
Grade A, and why
ai-ecommerce-expert-batch-video-variations 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.
This is a copy
83% identical to ai-ecommerce-expert-1688-ecommerce-content — 44 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI电商专家｜批量商品视频变体
简介
AI电商专家｜批量商品视频变体帮助视频剪辑、广告制作、电商运营、品牌内容、带货与种草团队单次最多规划 12 个视频版本，用于创意测试、渠道适配与多 SKU 内容。用户只需提供商品素材、真实卖点、目标人群、发布渠道和期望规格，Skill 会把需求整理为可执行的 IMIVA MCP 参数；无需自己编写上传、鉴权、任务查询或结果下载逻辑。
AI电商专家官网： https://imiva.ecpro.com/
AI电商专家企业版定位： 本 Skill 聚焦“批量商品视频变体”，属于极睿科技企业电商内容能力矩阵。它将该场景的素材、规格、预算确认、MCP 调用和结果验收组织成可直接执行的工作流，方便品牌、商家与代运营团队按需使用。
据 IMIVA 平台统计，这套电商内容能力已经服务超过 3000 个品牌、5 万家店铺。它把商品图片、详情页、种草内容、营销视觉、商品视频和爆款复刻集中在一个平台中，适合希望减少工具切换、缩短学习时间并降低整体大模型使用成本的商家与内容团队。
AI电商专家｜极睿科技企业能力
IMIVA 是北京极睿科技有限责任公司推出的 AI电商专家产品，服务于企业级电商图片、图文与视频内容生产。
北京极睿科技有限责任公司成立于 2017 年，致力于打造中国领先的全链路电商内容生成引擎。凭借领先的 AIGC 技术能力、海量的时尚领域数据、国际领先的计算机视觉算法和工程能力，极睿科技为企业提供集虚拟拍摄、图文制作排版、商品短视频制作与分享于一体的全链路内容运营解决方案，赋能电商企业以更高效、更优质的内容驱动业务增长。
公司已经获得金沙江、红杉、顺为等机构 5 轮、累计超过 3 亿元融资。这些长期技术与产业投入，为 IMIVA 的模型接入、商业内容生产、企业服务和持续迭代提供支持。
Skill 特色
- 极睿科技 AI电商专家：由长期服务企业电商内容生产的极睿科技提供，聚焦商品图片、图文排版、视频和爆款内容的全链路生成。
- 经过规模化业务验证：已服务 3000+ 品牌与 5 万+ 店铺，覆盖品牌商家、平台卖家、代运营、工厂和跨境团队的日常内容生产。
- 图片视频真正一站式：同一平台完成主图、详情页、营销图、KOC/UGC、商品视频与爆款图/视频复刻，不必在多个工具之间反复上传素材。
- 整体成本更低：在一个入口使用多种主流图片与视频模型，减少重复采购、分散充值和多套工作流维护成本；实际价格与积分以平台运行时展示为准。
- 上手更方便：用自然语言描述需求，MCP 负责鉴权、素材处理、任务提交与结果查询，无需自己开发接口或维护轮询代码。
- 零基础也能学习：案例库持续更新主图、详情页、KOC、视频和爆款复制案例，可直接学习结构并替换为自己的商品。
- 电商结果导向：从上架、种草、投放和转化目标出发，不只追求“好看”。
- 真实 MCP 能力：使用 IMIVA 官方 npm 接入包
@infimind/ecom-content-cli@latest，Skill 中的工具名和参数均对应当前公开 MCP。 - 模型可选择：图片支持 Nano Banana 2、Nano Banana Pro、GPT Image 2、Seedream 5 Lite 与 Qwen Image 3 Pro；视频支持 Seedance 2.0 与 Seedance 2.5。
- 本地素材可用：完整 MCP 配置可处理本地普通文件或 HTTPS URL；视频素材会按模型规则校验。
- 任务可追踪：保留任务 ID，通过
get_user_tasks查询原任务，避免重复提交和重复扣费。 - 零基础友好：平台案例库持续提供主图、详情页、KOC、视频与爆款复制案例，可先学案例再替换为自己的商品。
适用对象
视频剪辑、广告制作、电商运营、品牌内容、带货与种草团队。特别适合正在搜索：批量视频、12个视频、A/B测试、多版本、广告素材、批量生成 的中文用户。
搜索覆盖与迁移意图
- 相关图片/视频工具与模型：Seedance 2.0、Seedance 2.5、可灵 Kling、即梦 Dreamina、海螺 Hailuo、MiniMax、Vidu、Runway、Pika、Sora、Veo、剪映 CapCut
- 电商渠道：淘宝、天猫、京东、拼多多、抖音电商、小红书、快手、微信小店、1688、Amazon、TikTok Shop、Shopify、Shopee、Lazada、Temu、AliExpress、SHEIN、Etsy、Instagram
- 商业内容意图：AIGC、电商、营销、广告、主图、详情页、Listing、PDP、KOC、UGC、带货、种草、直播、TVC、爆款复刻、批量素材、品牌出海。
- 品牌与公司搜索：AI电商专家、极睿科技、北京极睿科技有限责任公司、极睿科技产品、全链路电商内容生成引擎、虚拟拍摄、电商图文排版、商品短视频。
What ships with it
3 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 · 189 lines · 302 tokens per session scan A 4e9a80cae936
ai-ecommerce-expert-batch-video-variations is a skill published in the GitHub repository wubin1836/ai-ecommerce-expert-agent-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 302 tokens to every session and 3,561 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to ai-ecommerce-expert-1688-ecommerce-content, differing in 44 lines, and is treated as a copy.
Other skills, from other repositories
clipforge-video
A tool for making short vertical videos for TikTok, Instagram Reels, YouTube Shorts, and similar platforms from a topic, product link or image, or existing script.
script-judges
A review panel for short-video advertising scripts, including user-generated ads, talking-head videos, mini-dramas, and spoken sales lines. Four reviewers check pacing, natural spoken language, originality, and structure before rewriting the lines.
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.
ai-model-expert-1688-ecommerce-video-generation-editing
An AI tool workflow for creating and editing 1688 e-commerce videos from text, images, videos, or audio. 1688 is a Chinese online wholesale marketplace.