这是Runway API的媒体生成技能包，能批量生成视频、图片和音频。支持seedance2、gen4.5、veo3、Nano、Banana Pro这些模型。有两种用法，一种是让Agent直接调API生成媒体，告诉它要什么就行，它会自动调用、轮询完成状态、下载结果，可以生成单个也能编排几百个；另一种是集成到自己的服务端项目里，Agent会帮你验证兼容性、设置凭证、写路由、处理文件上传和任务轮询这些边界情况。支持Claude Code、Cursor、Codex等Agent，适合做广告素材批量生成、产品视频、多镜头故事这些创意迭代场景。
查看英文原文
Runway API Skills Media Generation at scale. One platform to run the best image, video, audio and real time models. Generate videos, images, and audio with Runway's API — batch Ad campaigns, product videos, multishot stories, and creative iteration. Supports seedance2, gen4.5, veo3, Nano, Banana Pro, and more. Works with Claude Code, Cursor, Codex, and other compatible agents. Two Ways to Use 1. Generate media at scale Tell your agent what to create and it handles the rest — calls the API, polls for completion, downloads the result. Generate one asset or orchestrate hundreds. [安装/使用命令见下方] [安装/使用命令见下方] [安装/使用命令见下方] 2. Integrate into your app Guide your agent through adding Runway capabilities to a server side project: verify compatibility, set up credentials, write framework specific routes, and handle edge cases like file uploads and task polling. [安装/使用命令见下方] Installation Claude Code (community marketplace) [安装/使用命令见下方] You can also run /plugin in Claude Code, open Discover , search for runway api skills , and install from there. After installing or updating plugins, run /reload plugins if skills do not appear immediately. Other agents ( npx skills ) [安装/使用命令见下方] Select all the skills with your keyboard (Space to select, arrow keys to navigate), then press Enter to install. Prerequisites A Runway developer account with prepaid credits ($10 minimum) For generation skills: uv (Python package runner) and RUNWAYML API SECRET env var For integration skills: a server side project — Node.js 18+ or Python 3.8+ with a backend framework Available Skills Generation (run directly) Generate media assets directly — your agent runs the scripts, polls for completion, and saves the output. Skill Description rw generate video Generate videos: text to video, image to video, video to video rw generate image Generate images: text to image with optional reference images rw generate audio Generate audio: TTS, sound effects, voice isolation, dubbing, voice conversion Integration (add to y