This skill generates and extends Gemini Veo 3.1 videos from text or images using the Python SDK, with configurable resolution, duration, and prompts.
npx playbooks add skill xiangyu-cas/vision-skills --skill video-generation
The Video Generation skill generates and extends Gemini Veo 3.1 videos from text or images using the Python SDK, allowing for configuration of resolution, duration, and prompts. This skill connects to the Python SDK and enables the creation and extension of videos based on provided inputs. A developer would use this skill when they need to generate videos from text or images with specific characteristics, such as resolution and duration.
Its 23-word system prompt specializes your agent in media & content with structured methodology and proven output formats. Install with one command to activate immediately.
This skill generates and extends Gemini Veo 3.1 videos from text or images using the Python SDK, with configurable resolution, duration, and prompts.
Video Generation is a free media & content skill for AI coding agents. This skill generates and extends Gemini Veo 3.1 videos from text or images using the Python SDK, with configurable resolution, duration, and prompts.. It provides a specialized system prompt that configures your agent with media & content expertise.
Run npx playbooks add skill xiangyu-cas/vision-skills --skill video-generation in your terminal to install Video Generation into your Claude Code session. It works immediately after installation.
Video Generation is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Yes, Video Generation is completely free and open source. The full source is available on GitHub at https://github.com/xiangyu-cas/vision-skills/tree/main/skills/video-generation. You only need a subscription to the AI agent you use it with.
Weekly roundup of top Claude Code skills, MCP servers, and AI coding tips.