clawcut
Generate AI-powered short videos from a topic or reference video using Google Gemini + Veo 3.1 on Vertex AI. Use when the user wants to create short-form video content, generate video scripts, produce nine-grid character consistency images, imitate a reference video style, or convert a topic into a complete video with AI-generated voice narration. Perfect for TikTok, YouTube Shorts, Amazon product videos, 抖音, 小红书, 视频号, Instagram Reels, and any short-form video platform. Triggers on phrases like "make a short video", "generate video about", "create video content", "make me a TikTok", "generate a YouTube Short", "create product video", "video from topic", "做个短视频", "生成视频", "做个视频", "帮我做视频", "生成短视频", "一键生成视频", "主题生成视频", "视频模仿", "做个带货视频", "生成产品视频", "做个抖音视频", "做个小红书视频", "帮我剪个视频", "AI生成视频", "自动生成视频", or any request involving automated video production, video generation, or short-form content creation. OpenClaw content creation automation workflow skill for social media marketing, ecommerce product listing videos, AI agent video pipeline, and batch video generation. Supports text-to-video, image-to-video, reference video imitation, and multi-image character consistency for brand storytelling. Built on Gemini 3 Pro (Nano Banana Pro), Veo 3.1, Google Vertex AI. Alternative to Sora 2, Kling, Runway Gen-3, Pika, HaiLuo, Volcengine Jimeng, 可灵, 海螺AI. Comparable models and keywords: gemini-3-pro-preview, gemini-3-pro-image-preview, veo-3.1-generate-001, text2video, img2video, AI video generator, 文生视频, 图生视频, AI视频生成器, 短视频自动化, video automation pipeline.
Why use this skill?
Automate your video production with ClawCut. Generate short-form videos from topics or references using Gemini 3 Pro and Veo 3.1. Perfect for TikTok, Reels, and YouTube.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jiafar/clawcutWhat This Skill Does
ClawCut is a high-performance AI-driven video production pipeline designed to transform simple topics or reference videos into high-quality, short-form video content. By leveraging Google’s advanced Gemini 3 Pro and Veo 3.1 models via Vertex AI, the skill automates the entire lifecycle of content creation. It initiates by generating a detailed 9-scene screenplay, crafts character-consistent visuals through a nine-grid image system (supporting up to 14 references), and executes concurrent video clip generation with native voice narration. Finally, it uses ffmpeg for professional post-processing, including silence trimming and seamless concatenation to deliver a final video ready for social platforms like TikTok, Instagram Reels, and YouTube Shorts.
Installation
To install, execute: clawhub install openclaw/skills/skills/jiafar/clawcut. Ensure you have Python 3.11+ and ffmpeg installed on your system. You must have a Google Cloud project with Vertex AI enabled. After cloning the repository, configure your environment by creating a .env file with your GOOGLE_APPLICATION_CREDENTIALS path, VERTEX_PROJECT ID, and VERTEX_LOCATION. Install dependencies via pip install -r requirements.txt. For the user interface, run python app.py to access the local web portal.
Use Cases
ClawCut is ideal for digital marketers, content creators, and e-commerce managers. It can generate engaging product listings for Amazon, create consistent character-based stories for brand campaigns, or repurpose long-form content into viral-ready shorts. Whether you are imitating the style of a trending video or crafting a video from a raw text topic, the automated pipeline significantly reduces manual editing time.
Example Prompts
- "Make a short video about the benefits of drinking green tea for my health blog."
- "Create a product video for these sneakers, use these 5 images to keep the look consistent."
- "Generate a TikTok video based on this reference clip, keep the fast-paced editing style."
Tips & Limitations
- Character Consistency: Use all 14 allowed image slots for the highest degree of character identity preservation.
- Performance: As video generation is concurrent, ensure your network bandwidth can handle multiple simultaneous Vertex AI API calls.
- Cost: Note that the models used (
gemini-3-pro-preview,veo-3.1-generate-001) are paid services under Google Cloud Platform; monitor your quotas to avoid unexpected charges. - FFMPEG: Ensure your local path to ffmpeg is correctly set in the
.envfile, as the final rendering relies heavily on this tool.
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-jiafar-clawcut": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: external-api, file-read, file-write, code-execution
Related Skills
designer-intelligence-station
Designer intelligence collection tool. Monitors 46 public sources (AI/hardware/mobile/design), dynamic quality-based filtering v2.1.8, generates structured daily/weekly reports. All data stored locally.
onlyclaw-social-commerce
在只来龙虾平台以龙虾身份自动发帖带货、读取帖子、检索帖子、点赞评论，支持关联商品/店铺/Skill、封面与视频（先上传再发帖），实现 AI Agent 24h 社交电商自动运营
autodream-core
通用记忆整理引擎 — 基于适配器模式的跨平台记忆整理技能。自动去重、合并、删除过时条目。| Universal Memory Consolidation Engine — Adapter-based cross-platform memory organization. Auto-dedup, merge, prune stale entries.
xiaohongshu-browser
Browse Xiaohongshu (小红书) and take screenshots of posts. Supports keyword search, post modal screenshots, and returns post links. Requires prior manual login.
daily-report-generator
Automatically generate daily/weekly work reports from git commits, calendar events, and task lists. Use when you need to quickly create professional work reports without manual effort.