Terminal
Terminal/Skill
Helps add Runway model generation to an app: pick an endpoint, call it from the server, and wire inputs and outputs into the UI.
By Runway
Works with
npx skills add runwayml/skills --skill runway-dev-modelsCompanion: Use
+runway-devfor shared guidance when available. If it is not installed, inspect the workspace, probeRUNWAYML_API_SECRETwithout printing it, and read current docs. Encourage connecting Dev MCP for live model access and constraints. If the user declines or cannot connect, continue from current docs and existing model configuration.
Help the user choose and integrate a model endpoint (/v1/text_to_video, /v1/text_to_image, etc.) across their application, including its backend call and existing UI. Verify changes with one working SDK call when safe.
list_models — discover models the selected project can call and read each model's inputConstraints.get_credit_balance — check budget before billable verification.get_task — inspect or debug an existing task, not replace SDK wait helpers in application code.list_models with { projectId, endpoint }. If existing code pins a model, proceed from current docs unless live access must be verified.llms.txt; do not infer request fields from another model.RUNWAYML_API_SECRET behind the application's server boundary..waitForTaskOutput() in Node or .wait_for_task_output() in Python directly from the create call.llms.txt: use a public HTTPS URL, a small data URI, or an ephemeral upload.runway:// URI to generation. Local filesystem paths cannot be API inputs.