图片上传
上传本地图片到云存储，获取公开访问的 URL 链接。当用户需要上传图片、转存网络图片、获取图片 URL 时使用此 skill。
Why use this skill?
Easily upload local images or remote URLs to stable cloud storage for use with AI models. Includes CDN support, auto-detection, and seamless integration with OpenClaw skills.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/hexiaochun/upload-imageWhat This Skill Does
The 图片上传 (Image Upload) skill serves as an essential bridge between local hardware and the cloud-based AI processing ecosystem. It acts as a gateway that takes raw image data—either as Base64 encoded strings or remote URL references—and persists them into a secure, globally accessible CDN-backed cloud storage. By converting ephemeral files or transient web links into stable, permanent URLs, this skill ensures that other OpenClaw AI models, such as video generators or image editors, can reliably fetch the input data they need to perform complex tasks. It handles formatting, MIME type detection, and storage organization, abstracting away the underlying infrastructure complexities from the user.
Installation
To integrate this capability into your OpenClaw agent, execute the following installation command in your terminal:
clawhub install openclaw/skills/skills/hexiaochun/upload-image
Use Cases
This skill is highly versatile for creative and administrative workflows. Use it when you need to:
- Media Production: Upload a local photo to initiate a 'photo-to-video' transformation task via Sora 2.
- Content Curation: Permanently store a fleeting internet image link to your private cloud to prevent broken links in future projects.
- Advanced Editing: Upload an image to serve as the reference source for generative image editing models like Flux 2 Flash.
- Archiving: Build a structured library of assets by specifying custom folders and file names for your visual content.
Example Prompts
- "Upload this local image from my computer and turn it into a short cinematic video using the Sora 2 model."
- "Grab this image from https://example.com/photo.jpg, save it to my 'project-assets' folder, and give me the new URL."
- "I have this product image file; can you upload it and prepare it for an AI image enhancement session?"
Tips & Limitations
- Efficiency: The tool accepts both direct Base64 chunks and web URLs, making it flexible for both local file interactions and web-based workflows.
- Auto-Detection: Don't worry about manual MIME type definitions; the tool automatically identifies formats like PNG, JPEG, or WebP if left blank.
- Limits: To maintain performance, keep individual file uploads under 10MB.
- Persistence: Unlike temporary cache, uploaded files are stored permanently in the 'fal-task' bucket, which is ideal for long-term project asset management.
- Format Scope: Note that this skill is currently optimized for static images only; media like MP4 or MOV files are not supported at this time.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-hexiaochun-upload-image": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-read, external-api
Related Skills
水浒传故事小人书
水浒传故事小人书创建。使用 Nano Banana Pro 模型生成手绘卡通风格的水浒传故事信息图。当用户想要创建水浒传故事插画、小人书、信息图时使用此 skill。
prop-extractor
从剧本中提取关键道具（武器、信物、法宝等），生成道具风格卡。当需要提取道具、建立道具库、生成道具描述时使用。
omnihuman-video
使用 OmniHuman v1.5 生成音频驱动的口型同步视频。当用户想要让图片中的人物说话、配音、口型同步，或提到 omnihuman 时使用此 skill。
视频链接解析
解析视频分享链接，获取无水印视频下载地址。当用户想要下载视频、解析抖音/快手/小红书/B站链接、获取无水印视频时使用此 skill。
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.