from dream-to-video-skill226
Convert a user's dream description into a cinematic video prompt, submit to a video-generation pipeline, and download the resulting video files (automated workf
Dream-to-Video converts freeform dream or diary text into a single, production-ready video prompt and automates submission to a video generation system (the repo targets the Jimeng platform). The skill includes environment setup instructions, worker/queue management, and post-processing steps to download and apply an 'elliptic shatter' effect to generated videos.
Agents that support browser automation or command execution (Playwright-enabled Python workers) and can run local scripts for queuing and downloading generated videos.
Dream-to-video skill converts user dream descriptions into cinematic video prompts and submits them to the 即梦 (Jimeng) platform via Playwright browser automation. SKILL.md is detailed and well-written in Chinese, with thorough prompt generation rules and edge case handling. No bundled scripts — all code lives in an external GitHub repo that the agent must clone and run. The setup process is heavy (Python deps, Playwright browser, platform login via QR code).
The skill instructs the agent to git clone an external repo and run pip install + playwright install without user confirmation, which is a security concern. No actual malicious intent detected, but the trust model assumes the external repo is safe. The prompt generation rules are impressively detailed with cinematic camera techniques and strict anti-hallucination guidelines. Niche usefulness — creative tool for dream visualization on a specific Chinese platform.
