aliyun-image阿里云百炼图像生成、编辑与翻译。文生图:根据文本生成图像,支持复杂文字渲染。图像编辑:单图编辑、多图融合、风格迁移、物体增删。图像翻译:翻译图像中的文字,保留原始排版,支持11种源语言和14种目标语言。触发词:生成图片、AI作画、文生图、图像编辑、修图、换背景、风格迁移、多图融合、图像翻译、图片翻译。模型:qwen-image-plus(默认)、qwen-image-max、qwen-image-edit-plus(默认)、qwen-image-edit-max、qwen-mt-image。
Install via ClawdBot CLI:
clawdbot install stanleychanh/aliyun-imageGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesisCalls external URL not in known-safe list
https://github.com/StanleyChanH/aliyun-image-skillAI Analysis
The skill sends data exclusively to the documented Alibaba Cloud DashScope API (dashscope.aliyuncs.com), which is consistent with its stated purpose of image generation and editing. No credential harvesting, hidden instructions, or obfuscation are present. The risk is low as it uses a legitimate, major cloud provider's service.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Generate high-quality product images from text descriptions for online listings, reducing photoshoot costs. Edit existing product photos to change backgrounds or styles, enhancing visual appeal. Translate text on product images for international markets, maintaining original design.
Create custom promotional graphics and social media visuals from textual ideas quickly. Edit campaign images to adapt for different platforms or audiences, such as changing styles or adding elements. Translate ad banners and posters into multiple languages while preserving layout and branding.
Produce illustrations and artwork for blogs, videos, or articles based on written prompts. Edit photos for visual storytelling, like merging multiple images or applying style transfers. Translate text in infographics or memes to reach global audiences without redesigning.
Generate educational diagrams and visual aids from textual concepts to enhance learning. Edit instructional images to update content or improve clarity, such as adding annotations. Translate textbooks and worksheets with embedded text, supporting multilingual education.
Offer pay-per-use API access for developers to integrate image generation, editing, and translation into their applications. Charge based on successful image generations, with tiered pricing for different model qualities. Attract startups and enterprises needing scalable visual content solutions.
License the skill as a white-label solution for agencies or SaaS providers to rebrand and resell to their clients. Provide customization options and support for specific industries like e-commerce or marketing. Generate revenue through subscription or licensing fees.
Integrate the skill into existing creative tools or platforms as a premium feature, offering basic functions for free and advanced capabilities via subscription. Upsell users on high-quality models or bulk processing options. Drive adoption through free tiers and monetize power users.
💬 Integration Tip
Ensure API keys are securely stored and requests match the same region as the key to avoid errors.
Scored May 26, 2026
抖音数据查询与工具助手。覆盖视频详情、用户数据、搜索、热榜、创作者工具、星图达人、内容指数等模块。含部分交互触发和协议工具接口(已标注)。
小红书全场景数据查询助手。支持App和Web多版本API,覆盖笔记详情、用户数据、搜索、商品、评论、话题等全功能。
小红书(RED/XHS)自动化助手。提供完整的小红书操作能力:登录、发布图文/视频、搜索笔记、浏览详情、点赞收藏评论、查看博主主页、内容策划。 当用户提到小红书、红书、XHS、RED、发笔记、搜笔记、小红书运营等任何与小红书相关的操作时使用此 skill,即使用户没有明确说"小红书"但描述的场景明显是小红书(如"...
知乎数据查询助手。覆盖用户信息、搜索、专栏、问答、热榜、评论等全功能。
今日头条数据查询助手。覆盖文章、视频、用户、评论等全功能。
微博全场景数据查询助手。整合App/Web/V2多版本API,覆盖微博详情、用户数据、AI搜索、高级搜索、热搜榜单、评论、视频等全功能。