mediastormDev/dream-to-video-skill

Registry

Summary

Dream-to-Video Skill is an AI agent skill that turns dream descriptions into cinematic videos. It auto-generates prompts, submits them to Jimeng via browser automation, and downloads finished videos with post-processing effects.

Key features

• Transforms dream descriptions into cinematic videos
• Auto-generates prompts for video generation
• Submits prompts to Jimeng via browser automation
• Downloads finished videos with post-processing effects
• Built as an AI agent skill for seamless integration

Use cases

• Creative storytelling from dream journals
• Rapid prototyping of video concepts
• Personalized cinematic content creation
• Educational visualization of abstract ideas
• Entertainment and artistic expression

README excerpt

# Dream-to-Video Skill [中文文档](./README.zh-CN.md) AI agent skill that transforms dream text into cinematic videos. Describe your dream, and the agent automatically generates professional video prompts, submits them to the [Jimeng](https://jimeng.jianying.com) platform via browser automation, downloads the finished videos, and applies post-processing effects. ## How It Works ``` Dream text → AI transforms to cinematic prompt → Queue → Browser automation → Jimeng platform → Download → Post-processing → Video files ``` 1. **Prompt transformation** — The AI agent converts your dream description into a detailed cinematic video prompt following 10 strict rules (photorealistic style, fisheye lens, no text overlays, silent narrative, etc.) 2. **Queue submission** — The prompt is added to a local task queue (SQLite + JSONL) 3. **Browser automation** — A background worker drives Chromium via Playwright to interact with the Jimeng video generation platform: login, submit prompts, upload reference images when needed, monitor progress 4. **Download & post-processing** — Completed videos are downloaded and automatically processed with an "Elliptic Shatter" edge effect (center-clear, shattered-glass edges), outputting both the original and the effect version ## Install ### Via skills CLI ```bash npx skills add mediastormDev/dream-to-video-skill -s dream-to-video ``` ### Manual install Clone the repo and symlink the skill directory into your agent's skill folder: ```bash git clone https://github.com/mediastormDev/dream-to-video-skill.git mkdir -p ~/.claude/skills ln -s "$(pwd)/dream-to-video-skill/skills/dream-to-video" ~/.claude/skills/dream-to-video ``` ## Requirements - Python >= 3.10 - Chromium (installed via Playwright) - An API key from any supported provider: | Prov

Topics

No topics yet.