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 virgoC0der/awesome-claude-code --skill product-video-promptgit clone --depth 1 https://github.com/virgoC0der/awesome-claude-codeWrote 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/virgoc0der/awesome-claude-code/product-video-prompt)<a href="https://agentmods.dev/skills/virgoc0der/awesome-claude-code/product-video-prompt"><img src="https://agentmods.dev/badge/skills/virgoc0der/awesome-claude-code/product-video-prompt/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/virgoc0der/awesome-claude-code/product-video-prompt"><img src="https://agentmods.dev/badge/skills/virgoc0der/awesome-claude-code/product-video-prompt.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 | $0.00224 | $0.05969 |
| Opus 5.5 | $0.00090 | $0.02388 |
| Sonnet 5.5 | $0.00045 | $0.01194 |
| Haiku 4.5 | $0.00022 | $0.00597 |
Grade A, and why
product-video-prompt 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 1mo 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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Video Prompt Generator (Pseudo-UGC Default)
把 Shopify 商品链接变成一个伪 UGC 英文视频 prompt，目标模型：Seedance（字节跳动文生视频），发布平台：海外 TikTok / Instagram Reels。
两种输出模式
| 模式 | 何时使用 | 风格特征 |
|---|---|---|
| Pseudo-UGC（默认） | 用户没特别要求 / 提到 UGC / TikTok / Reels / 达人 / "真实感" | 第一人称 POV，对镜头讲述，手持感，生活化场景，真实质感 |
| Brand Mode（可选） | 用户明确说"品牌视频"、"高级感"、"brand"、"commercial"、"广告大片" | 电影感镜头、精致场景、第三人称叙事、品牌调性 |
默认走 Pseudo-UGC。只有当用户明确要求品牌感时才切 Brand Mode。
两种模式的前 4 步（数据抓取、看图分析、亮点提炼、参考图选择）完全一样，区别只在 Step 5 生成 prompt 时的模板。
Workflow
Step 1: 获取商品数据
从用户提供的 Shopify 商品链接获取数据：
- 提取域名和 handle：
https://example.com/products/cool-shoe→example.com+cool-shoe - 优先 products.json：请求
https://{domain}/products/{handle}.json，成功即解析 JSON - Fallback：web_fetch 商品页 URL，从 HTML 提取
必需字段：title、description、images（所有 URL）、variants、price、tags、product_type、vendor。
视频资源（重要）：很多 Shopify 商品页面带有官方产品视频，通常嵌在图片 gallery 里，格式是 .mp4 文件。获取视频 URL 的方式：
products.json不返回视频——必须用web_fetch拿商品页 HTML- 在 HTML 里搜索
cdn/shop/videos/或.mp4关键字 - 典型 URL 模式：
https://{domain}/cdn/shop/videos/c/vp/{hash}/{hash}.HD-1080p-*.mp4
找到的视频要作为重要资产记录下来——它在 Step 5 生成 prompt 时可以作为 [MOTION REFERENCE] 提供给 Seedance（图生视频模式，或直接作为动作参考说明）。这对有复杂机械动作的产品（开合、折叠、变形）特别有用——参考视频比任何文字描述都准确。
如果没找到视频，记录为 "No official product video available"，不影响流程继续。
Step 2: 看图（+ 看视频）分析 — 提取硬信息
看 3-5 张关键图，必须提取：
硬信息（给全局约束用）：
- 确切颜色（"哑光黑"而不是"黑色"）
- 材质（仿皮革/网布/橡胶/金属/磨砂塑料等）
- Logo 信息（位置、颜色、内容）
- 结构部件（几条拉链、几个扣子、是否对称）
- 关键图形元素（条纹/人字纹/图案，具体位置）
叙事信息：
- 产品品类（鞋类 / 服饰 / 3C / 美妆 / 家居 / 食品 / 运动 / 包袋配饰）
- 可动部件
- 目标人群画像（年龄、性别、生活方式、兴趣）
- 使用场景
如果有产品视频，额外提取（用文字描述视频内容，不要求真的能播放视频）：
- 视频里产品如何被操作（动作顺序、节奏、方向）
- 关键变形过程的分解（比如"0-2s 拉链从 A 拉到 B"）
- 手 / 脚 / 产品的相对位置和进入画面的角度
- 操作的快慢节奏（是一气呵成还是分步停顿）
这些信息在 Step 5 写 [MOTION REFERENCE] 块时直接用，避免让模型"凭空想象"动作过程。
Step 3: 提炼商品亮点
3-5 个核心卖点。每个包含：
- 亮点名称（简短）
- 一句话描述（突出差异化）
- 英文短 tagline（后续可能变叠字或台词碎片，不超过 8 英文字）
优先级：功能性 > 视觉/设计 > 情感/场景。
Step 4: 选择 UGC 人设（仅 Pseudo-UGC 模式）
What ships with it
1 file 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.
- 1mo ago First seen · 458 lines · 224 tokens per session scan A e0edffdd0d5b
product-video-prompt is a skill published in the GitHub repository virgoC0der/awesome-claude-code (1 stars, last pushed 1mo ago), licensed MIT. It adds 224 tokens to every session and 5,969 once invoked, about $0.0009 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 2026-09-12.
product-video-prompt compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-video-promptvirgoC0der/awesome-claude-code | Skill | 1 | 1mo ago | MIT | A | 224 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | today | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | yesterday | MIT | A | 111 | Claude Code |