openrouter-video-generatelisted

# OpenRouter Video Generation Use this skill to submit asynchronous OpenRouter video jobs, poll them to a terminal state, and save completed video files. ## Default workflow 1. Use the OpenRouter API key from the current environment first. If it is missing, rely on the bundled script's automatic lookup of the nearest project `.env` file containing `OPENROUTER_API_KEY`, unless the user explicitly provides another environment variable name or env file path. 2. Pick a model from the user's request. If no model is specified, use `bytedance/seedance-2.0` and mention that the user can override it. Use model discovery before assuming support for unusual resolutions, aspect ratios, audio, images, or provider options. 3. Use `scripts/openrouter_video_generate.py` rather than constructing requests and polling loops manually. 4. Save generated videos to a user-visible output directory, defaulting to the current working directory if the user did not specify one. 5. Do not print API keys or put them directly on the command line because shell history may capture them. ## Bundled script Submit, wait, and download in one command: ```bash python scripts/openrouter_video_generate.py generate \ --prompt "a slow cinematic push-in on a neon cafe sign in the rain" \ --model "bytedance/seedance-2.0" \ --duration 5 \ --resolution 1080p \ --aspect-ratio 16:9 \ --output-dir ./outputs ``` The script reads `OPENROUTER_API_KEY` from the current environment first. If it is not set, it s