cn-video-gen
国产AI视频生成技能。支持通义万相（Wan2.6文生视频/图生视频）和可灵（Kling V2）。适合创意视频制作、图生视频、动态内容生成等场景。当用户要求生成视频、将图片生成动态视频、或基于描述生成视频片段时触发。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/dadaniya99/cn-video-genWhat This Skill Does
The cn-video-gen skill is a comprehensive tool for OpenClaw AI agents to generate professional-grade videos using leading domestic Chinese AI platforms. It integrates two powerful services: Alibaba's Tongyi Wanxiang (Wan2.6) for versatile text-to-video and image-to-video synthesis, and Kuaishou's Kling (V2) for high-fidelity, motion-intensive scenes. This skill streamlines the entire creative pipeline, from handling image uploads to managing API requests, polling for task completion, and delivering the final video content directly to your workspace.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/dadaniya99/cn-video-gen
Ensure you have configured your environment variables, specifically DASHSCOPE_API_KEY for Wanxiang and the KLING_ACCESS_KEY / KLING_SECRET_KEY pair for Kling, as defined in the project documentation.
Use Cases
- Creative Content Production: Quickly generate B-roll footage or cinematic sequences based on detailed text prompts.
- Dynamic Storytelling: Transform static product photos or portraits into engaging motion videos using the I2V capability.
- Storyboard Visualization: Utilize the multi-shot narrative feature to create complex video sequences for directors and creators.
- Social Media Marketing: Produce short, high-quality video clips for marketing campaigns efficiently.
Example Prompts
- "帮我生成一段5秒的视频，画面是一个女孩在雨中的街道奔跑，情绪忧郁，画质1080P。"
- "把这张图变成一段动态视频，让海浪拍打礁石，夕阳红光在水面跳动。"
- "我想拍一部短片，使用可灵模型生成一段镜头缓缓推近的森林探险片段。"
Tips & Limitations
- Cost Efficiency: Start with 720P resolution for prompt verification before committing to 1080P/15s renders. Failed tasks are not charged.
- Prompt Engineering: Use descriptive motion verbs (e.g., "camera slowly pushes in", "tracking shot") rather than just static descriptions. Subject positioning at the start of the prompt yields better results.
- Workflow: For I2V tasks, ensure your local images are uploaded to the authorized image host first. Always download generated videos promptly, as the API source URLs have a limited expiration time.
- Reliability: The skill utilizes an asynchronous polling mechanism; please allow 1-5 minutes for processing depending on current server load.
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-dadaniya99-cn-video-gen": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api, code-execution
Related Skills
evomap-gep
Connect any OpenClaw agent to the EvoMap collaborative evolution marketplace via the GEP-A2A protocol — no evolver required. Activate when the user or agent mentions EvoMap, wants to search for capsules or genes from other agents, publish a solution, or learn the GEP protocol. sender_id is auto-detected from MEMORY.md — each agent just saves their node ID once and the scripts handle the rest.
feishu-card
飞书互动卡片发送技能（国际版 Feishu 兼容）。当需要发送格式丰富的飞书卡片消息时使用。支持标题、Markdown 内容、颜色主题。关键：必须使用 schema 2.0 格式 + 双重 JSON stringify，否则国际版飞书（Feishu）无法渲染。
pdf-ocr
PDF扫描件转Word文档。支持中文OCR识别，自动裁掉页眉页脚，保留插图，彩色章节封面页保留为图片。使用百度OCR API（免费额度1000次/月）。当用户要求把扫描PDF转成文字/Word时触发。
sketch-illustration
插画图片生成技能，支持多种手绘风格。使用 Imagen 3（ZenMux API）生成插图，适合流程图、功能说明、PPT配图、教程配图、知识图和手绘信息图等场景。支持四种风格：A) Sketch 极简手绘风（Notion/Linear 风格，简笔人物，冷淡低饱和）；B) Watercolor 奶油彩铅水彩风（暖色调，纸纹彩铅，适合PPT讲义）；C) Flat Vector Retro 扁平矢量复古风（黑色轮廓线，几何简化，复古配色，适合NotebookLM PPT/课程封面）；D) Doodle Infographic 白纸手绘知识图风（白纸背景、拟人角色、高信息密度、手账/课堂板书感，适合概念对比、方法论、拖延机制、知识卡片）。生成后自动上传发送到飞书。当用户要求生成插画、配图、手绘风格图、流程示意图、产品插图、PPT配图、知识图、信息图、手绘知识海报时触发此技能。
eudic-vocab
欧路词典生词本管理与每日测试技能。支持自动从欧路词典收藏夹出题、管理单词、删除已掌握词汇。适合每日背单词使用。