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 aliang2052/aliang-skills --skill aliang-product-detail-photosgit clone --depth 1 https://github.com/aliang2052/aliang-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/aliang2052/aliang-skills/aliang-product-detail-photos)<a href="https://agentmods.dev/skills/aliang2052/aliang-skills/aliang-product-detail-photos"><img src="https://agentmods.dev/badge/skills/aliang2052/aliang-skills/aliang-product-detail-photos/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/aliang2052/aliang-skills/aliang-product-detail-photos"><img src="https://agentmods.dev/badge/skills/aliang2052/aliang-skills/aliang-product-detail-photos.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 | $0.00033 | $0.00884 |
| Opus 5 | $0.00016 | $0.00442 |
| Sonnet 5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
aliang-product-detail-photos 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.
What it actually says
商品详情图生成器
依赖： 阿里云百炼 CLI (
bl)，需配置DASHSCOPE_API_KEY。
触发词
当用户提到"商品详情图"、"电商主图"、"产品图"、"去掉背景"、"做产品宣传图"时使用。
工作流
第一步：确认需求
向用户确认：
- 图片数量 — 需要几张（用户必须指定）
- 产品图片 — 原图路径
- 图片比例 — 1:1 方图 / 3:4 竖图 / 16:9 横图（默认 3:4）
- 风格偏好 — 简约 / 温馨 / 自然 / 科技感 等（默认简约）
- 输出目录 — 默认
输出/
第二步：产品理解与场景规划
用 bl text chat 分析产品，规划拍摄方案：
bl text chat --message "你是一位专业的电商摄影师。请分析产品图片，规划商品详情图拍摄方案。
产品图片：{product_image_path}
需要生成：{n}张，风格：{style}
请输出规划表，将{n}张图片拆分为「角度」+「场景」的组合，每张说明展示角度、场景背景、构图要点、光线氛围。"
向用户展示规划表，等待确认。
第三步：去除产品背景
bl image edit \
--image {product_image_path} \
--prompt "Remove the background completely, keep only the product itself with clean edges, output on solid white background" \
--model qwen-image-2.0-pro \
--out-dir {output_dir} \
--out-prefix "product_no_bg"
第四步：逐张生成详情图
对每张图，用去背景后的产品图放入场景（效果比纯文本生成更准确）：
bl image edit \
--image {product_no_bg_path} \
--prompt "Place this product naturally in {scene_description}, {composition_details}, {lighting_details}, professional product photography, sharp focus, no text, no watermark, no logo" \
--model qwen-image-2.0-pro \
--size "{ratio}" \
--out-dir {output_dir} \
--out-prefix "product_{index}"
场景建议：
- 食品/饮料 → 餐桌、厨房、自然光线
- 服装/鞋帽 → 模特穿搭、纯色背景、生活场景
- 数码产品 → 简约科技风、办公桌面
- 儿童用品 → 温馨家居、明亮色彩
- 户外用品 → 自然风光、使用场景
第五步：整理输出
输出报告：
✅ 商品详情图生成完成
📁 输出目录：{output_dir}/{product_name}/
📊 共生成 {n} 张图片：
- product_no_bg.png — 去背景产品图
- product_01.png — [角度] + [场景]
...
关键命令
| 操作 | 命令 |
|---|---|
| 去背景 | bl image edit --image <path> --prompt "Remove background..." --model qwen-image-2.0-pro |
| 产品入场景 | bl image edit --image <no_bg_path> --prompt "Place in {scene}..." --model qwen-image-2.0-pro --size "1:1" |
| 纯文本生成 | bl image generate --prompt "<description>" --model qwen-image-2.0-pro --size "3:4" |
| 产品分析 | bl text chat --message "<analysis prompt>" |
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.
- 12d ago First seen · 94 lines · 33 tokens per session scan A d735fc1662aa
aliang-product-detail-photos is a skill published in the GitHub repository aliang2052/aliang-skills (26 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 884 once invoked, about $0.0002 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
food-beverage-content-production
Provider-independent production guidance for AI agents creating or retouching appetizing food and beverage images, recipe videos, restaurant/menu visuals, CPG ads, ecommerce product images, beverage pours, packaging/lifestyle shots, and social food clips, including truthfulness, labeling/claims discipline, styling…
ecommerce-product-imagery
Provider-independent ecommerce product imagery production for marketplace listings, product pages, hero shots, lifestyle scenes, comparison charts, infographics, variant/packaging images, virtual try-on or placement mockups, ads, and AI-assisted product visuals. Use when an agent must plan, generate, edit, review…
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.
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.