alphashop-image

AlphaShop(遨虾)图像处理 API 工具集。支持11个接口:图片翻译、图片翻译PRO、 图片高清放大、图片主题抠图、图片元素识别、图片元素智能消除、图像裁剪、 虚拟试衣(创建+查询)、模特换肤(创建+查询)。 触发场景:图片翻译、翻译图片文字、放大图片、高清放大、抠图、去背景、 检测水印/Logo/文字、消除水印、去牛皮癣、裁剪图片、虚拟试衣、AI试衣、 模特换肤、换模特、AlphaShop图像、遨虾图片处理。

3,891 stars
Complexity: easy

About this skill

The alphashop-image skill integrates AlphaShop's comprehensive suite of AI-powered image processing tools directly into an AI agent's capabilities. It enables the agent to perform a wide range of image manipulations, including translating text within images (standard and PRO versions), upscaling images to high definition, intelligently extracting main subjects, identifying elements within an image, and removing unwanted elements smarty. Additionally, it supports precise image cropping. Beyond basic manipulations, the skill offers advanced functionalities critical for e-commerce and fashion, such as creating and querying virtual try-on tasks for clothing, and model skin changing. By automating these complex visual tasks, users can streamline content creation, enhance product imagery, and localize visual content efficiently, making it invaluable for businesses operating in dynamic online markets. Users would leverage this skill to quickly process large volumes of images, prepare product photos for different markets, generate marketing assets, or enhance the quality and appeal of visual content without requiring manual design work. The agent handles the API calls and parameter passing, simplifying the user's interaction with powerful image AI.

Best use case

The primary use case is for e-commerce sellers, content creators, and marketing professionals who need to rapidly process, enhance, localize, or modify product images and other visual content. This skill streamlines tasks like preparing product listings for international markets, creating compelling marketing visuals, or offering interactive shopping experiences like virtual try-on, significantly reducing manual effort and time.

AlphaShop(遨虾)图像处理 API 工具集。支持11个接口:图片翻译、图片翻译PRO、 图片高清放大、图片主题抠图、图片元素识别、图片元素智能消除、图像裁剪、 虚拟试衣(创建+查询)、模特换肤(创建+查询)。 触发场景:图片翻译、翻译图片文字、放大图片、高清放大、抠图、去背景、 检测水印/Logo/文字、消除水印、去牛皮癣、裁剪图片、虚拟试衣、AI试衣、 模特换肤、换模特、AlphaShop图像、遨虾图片处理。

Users should expect processed image URLs or task IDs for asynchronous operations, resulting in translated, enhanced, or modified images suitable for e-commerce, marketing, or other content needs.

Practical example

Example input

Translate the text in this product image from Chinese to English: `https://example.com/product_cn.jpg`

Example output

Image translation successful. You can view the translated image at: `https://api.alphashop.cn/processed_images/product_en.jpg`

When to use this skill

  • When you need to translate text within product images for international marketplaces.
  • To upscale low-resolution product photos or marketing images to high definition.
  • For automatically removing backgrounds from product images or intelligently removing unwanted elements like watermarks.
  • To generate virtual try-on images for clothing or change model appearances for e-commerce.

When not to use this skill

  • If you require highly artistic or subjective image editing that demands human judgment.
  • For offline image processing tasks where internet access to the AlphaShop API is unavailable.
  • If the images contain sensitive information that cannot be processed by a third-party API.
  • When only basic image manipulation (e.g., simple resizing without AI upscaling) is needed and can be done locally.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/alphashop-image/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/1688aiinfra/alphashop-image/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/alphashop-image/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How alphashop-image Compares

Feature / Agentalphashop-imageStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityeasyN/A

Frequently Asked Questions

What does this skill do?

AlphaShop(遨虾)图像处理 API 工具集。支持11个接口:图片翻译、图片翻译PRO、 图片高清放大、图片主题抠图、图片元素识别、图片元素智能消除、图像裁剪、 虚拟试衣(创建+查询)、模特换肤(创建+查询)。 触发场景:图片翻译、翻译图片文字、放大图片、高清放大、抠图、去背景、 检测水印/Logo/文字、消除水印、去牛皮癣、裁剪图片、虚拟试衣、AI试衣、 模特换肤、换模特、AlphaShop图像、遨虾图片处理。

How difficult is it to install?

The installation complexity is rated as easy. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# AlphaShop 图像处理

通过 `scripts/alphashop_image.py` 调用遨虾图像处理 API。

## 前置配置(必须先完成)

⚠️ **使用本 SKILL 前,必须先配置以下环境变量,否则所有接口调用都会失败。**

| 环境变量 | 说明 | 必填 | 获取方式 |
|---------|------|------|---------|
| `ALPHASHOP_ACCESS_KEY` | AlphaShop API 的 Access Key | ✅ 必填 | 可以访问1688-AlphaShop(遨虾)来申请 https://www.alphashop.cn/seller-center/apikey-management ,直接使用1688/淘宝/支付宝/手机登录即可 |
| `ALPHASHOP_SECRET_KEY` | AlphaShop API 的 Secret Key | ✅ 必填 | 可以访问1688-AlphaShop(遨虾)来申请 https://www.alphashop.cn/seller-center/apikey-management ,直接使用1688/淘宝/支付宝/手机登录即可 |

**⚠️ AlphaShop 接口欠费处理:** 如果调用 AlphaShop 接口时返回欠费/余额不足相关的错误,**必须立即中断当前流程**,提示用户前往 https://www.alphashop.cn/seller-center/home/api-list 购买积分后再继续操作。

### 配置方式

在 OpenClaw config 中配置:
```json5
{
  skills: {
    entries: {
      "alphashop-image": {
        env: {
          ALPHASHOP_ACCESS_KEY: "YOUR_AK",
          ALPHASHOP_SECRET_KEY: "YOUR_SK"
        }
      }
    }
  }
}
```

如果用户没有提供这些密钥,**必须先询问用户获取后再继续操作**。

## 命令速查

脚本路径:`scripts/alphashop_image.py`

### 同步接口(直接返回结果)

| 命令 | 功能 | 必填参数 |
|------|------|----------|
| `translate` | 图片翻译 | `--image-url` `--source-lang` `--target-lang` |
| `translate-pro` | 图片翻译PRO(源语种可传auto) | `--image-url` `--source-lang` `--target-lang` |
| `enlarge` | 图片高清放大 | `--image-url` |
| `extract-object` | 主题抠图 | `--image-url` `--transparent true/false` |
| `detect-elements` | 元素识别 | `--image-url` |
| `remove-elements` | 元素智能消除 | `--image-url` + 至少一个消除标记 |
| `crop` | 图像裁剪 | `--image-url` |

### 异步接口(提交任务 → 查询结果)

| 命令 | 功能 | 必填参数 |
|------|------|----------|
| `virtual-try-on` | 创建虚拟试衣任务 | `--clothes 'URL,TYPE'` `--count N` |
| `query-try-on` | 查询虚拟试衣结果 | `--task-id` |
| `change-model` | 创建模特换肤任务 | `--image-url` `--model-type` `--bg-style` `--age` `--gender` `--num` |
| `query-change-model` | 查询模特换肤结果 | `--task-id` |

## 使用示例

```bash
# 图片翻译(中文→英文)
python scripts/alphashop_image.py translate \
  --image-url "https://example.com/img.jpg" \
  --source-lang zh --target-lang en

# 图片翻译PRO(自动识别源语种)
python scripts/alphashop_image.py translate-pro \
  --image-url "https://example.com/img.jpg" \
  --source-lang auto --target-lang ru

# 高清放大4倍
python scripts/alphashop_image.py enlarge \
  --image-url "https://example.com/img.jpg" --factor 4

# 抠图(透明底)
python scripts/alphashop_image.py extract-object \
  --image-url "https://example.com/img.jpg" --transparent true

# 抠图(白色背景)
python scripts/alphashop_image.py extract-object \
  --image-url "https://example.com/img.jpg" --transparent false --bg-color "255,255,255"

# 元素识别(检测主体水印+文字,返回OCR)
python scripts/alphashop_image.py detect-elements \
  --image-url "https://example.com/img.jpg" \
  --object-elements 1 3 --return-character

# 消除非主体水印和文字
python scripts/alphashop_image.py remove-elements \
  --image-url "https://example.com/img.jpg" \
  --noobj-watermark 1 --noobj-character 1

# 裁剪到800×800
python scripts/alphashop_image.py crop \
  --image-url "https://example.com/img.jpg" \
  --target-width 800 --target-height 800

# 虚拟试衣(指定模特+上装)
python scripts/alphashop_image.py virtual-try-on \
  --model-images "https://example.com/model.jpg" \
  --clothes "https://example.com/shirt.jpg,tops" --count 1

# 查询虚拟试衣结果
python scripts/alphashop_image.py query-try-on --task-id "abc123"

# 模特换肤(白人青年女性,自然背景)
python scripts/alphashop_image.py change-model \
  --image-url "https://example.com/img.jpg" \
  --model-type WHITE --bg-style NATURE --age YOUTH --gender FEMALE --num 2

# 查询模特换肤结果
python scripts/alphashop_image.py query-change-model --task-id "xyz456"
```

## 异步任务流程

虚拟试衣和模特换肤为异步接口:
1. 调用 `virtual-try-on` 或 `change-model` 提交任务,获得 `taskId`
2. 等待几秒后调用 `query-try-on` 或 `query-change-model` 查询结果
3. 如果任务未完成,等待后重试查询

## API 详细文档

完整参数说明见 `references/api-docs.md`。

Related Skills

alphashop-text

3891
from openclaw/skills

AlphaShop(遨虾)文本处理 API 工具集。支持3个接口:大模型文本翻译、 生成商品多语言卖点、生成商品多语言标题。 触发场景:翻译文本、文字翻译、多语言翻译、生成卖点、商品卖点、 多语言卖点、生成标题、商品标题、多语言标题、SEO标题、 AlphaShop文本、遨虾文本处理。

Content & Documentation

alphashop-sel-product-search

3891
from openclaw/skills

商品搜索API SKILL:通过关键词搜索发现Amazon/TikTok平台商品。 支持价格、销量、评分、上架时间等多维度筛选条件。 通过 AlphaShop REST API 调用遨虾AI选品系统的商品搜索服务。

E-commerce & Product Sourcing

alphashop-sel-newproduct

3891
from openclaw/skills

AlphaShop新品选品SKILL:基于关键词和商品筛选条件生成深度市场分析和新品推荐报告。 支持Amazon和TikTok平台的跨境电商选品,提供市场评级、竞争分析、新品推荐、热销品对比等功能。

Data & Research

image-gen

3891
from openclaw/skills

Generate AI images from text prompts. Triggers on: "生成图片", "画一张", "AI图", "generate image", "配图", "create picture", "draw", "visualize", "generate an image".

Content & Documentation

keevx-image-to-video

3891
from openclaw/skills

Use the Keevx API to convert images to videos. Supports multiple models (V/KL), various resolutions (720p/1080p/4K), and audio generation. Use this skill when the user needs to: (1) Convert images to video (2) Generate video with Keevx (3) Create and query image-to-video tasks (4) Batch image-to-video conversion. Keywords: image to video, Keevx, video generation.

keevx-image-generate

3891
from openclaw/skills

Use the Keevx API to generate images from prompts and reference images. Supports standard and professional modes, multiple quality levels (1K/2K/4K), various aspect ratios, and batch generation. Use this skill when the user needs to: (1) Generate images from text prompts (2) Create AI images with reference images (3) Batch image generation (4) Query image generation task status. Keywords: image generate, Keevx, AI image, text to image.

🎨 Pollinations Image Generation Skill

3891
from openclaw/skills

A clean, modular, and user-friendly image generation tool powered by [Pollinations.ai](https://pollinations.ai).

doubao-image-gen

3891
from openclaw/skills

使用豆包 Seedream 模型文生图,支持并发批量生成,输出图库预览页

rynjer-image-generation

3891
from openclaw/skills

No description provided.

image-understanding

3891
from openclaw/skills

使用智谱AI的GLM-4V-Flash免费多模态API理解图片内容。当用户需要理解图片内容、描述图片、识别图中物体时使用此skill。

openai-image-gen

3891
from openclaw/skills

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

feishu-image-sender - 飞书图片发送技能

3891
from openclaw/skills

**智能图片发送工具,支持系统截图、本地图片发送,自动处理大图片压缩和双版本发送。**