libtv-skill
agent-im 会话技能 - 通过 liblib.tv 的 AI 能力生成和编辑图片/视频。覆盖场景包括：生成（文生图、文生视频、图生视频、做动画、画一个xxx、来段xxx）、编辑修改（把xxx换成yyy、去掉xxx、加上xxx、改成xxx、调整xxx、局部修改、改镜头）、风格转换（风格迁移、转绘、换风格）、视频续写延长、复刻视频/TVC/宣传片、短剧/短漫剧生成、音乐MV生成、产品广告/展示片制作、分镜/故事板设计、教育视频/短视频制作。当用户提到 liblib、libtv、上传参考图/视频、查看生成进度时也应触发。关键判断：只要用户的请求涉及 AI 图片或视频的创作、生成、编辑、修改，无论措辞如何（如"画只猫"、"做个海报"、"把纸船换成爱心"、"这个视频帮我改一下"、"帮我复刻这段视频"、"用这首歌做个MV"、"一句话生成短剧"），都必须触发此技能。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/316530790/libtv-skillsWhat This Skill Does
The libtv-skill is a comprehensive AI-powered multimedia creation and editing suite integrated into the OpenClaw agent ecosystem. Powered by LiblibAI’s advanced platform, this skill empowers agents to function as professional creative directors. It leverages state-of-the-art models like Seedance 2.0, Kling 3.0, and Wan 2.6 to handle everything from simple text-to-image generation to the production of high-end commercial TVCs, music videos, and complex short dramas.
Beyond simple generation, the skill excels at sophisticated image and video manipulation. It understands semantic editing requests such as 'swap the object,' 'apply style transfer,' 'adjust the camera angle,' or 'extend the video duration.' By orchestrating multi-step workflows—including file uploading to secure OSS storage, model selection, progress polling, and automated local downloading—the skill handles the entire creative lifecycle without requiring manual oversight.
Installation
You can install this skill directly via the OpenClaw hub. Ensure you have your LIBTV_ACCESS_KEY configured in your environment variables before deployment. Execute the following command in your terminal:
clawhub install openclaw/skills/skills/316530790/libtv-skills
Use Cases
- Marketing & Advertising: Create professional product展示片 (showcase videos) or edit existing TVCs by swapping branding or adjusting visual styles.
- Content Creation: Generate consistent short-form content, from storyboards and animation sequences to full-length music videos.
- Visual Editing: Perform local object replacements, background removals, or frame-level modifications on uploaded assets.
- Education: Automate the creation of educational shorts and visual aids using descriptive prompts.
Example Prompts
- "画一只在火星上喝咖啡的机械猫，风格要赛博朋克一点。"
- "把这个视频里的纸船换成爱心，保留原本的背景和光影。"
- "我有一首背景音乐，请根据这段旋律帮我生成一段 MV 视频。"
Tips & Limitations
- Pre-Processing: Always upload reference images or videos before sending an edit request to ensure the agent has access to your assets via a valid OSS URL.
- Polling: For complex tasks like short dramas or multi-scene MV generation, the process is asynchronous. Use the
query_session.pyscript periodically to track progress. - Data Size: Ensure all uploaded reference files are under 200MB.
- Workflow Automation: The tool is designed to automatically download results upon completion; ensure your target output directory has sufficient disk space.
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-316530790-libtv-skills": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api