
自媒体视频动效 · 人物后大字接全屏宣言
装上下面任意一个 Skill,再让你的 Agent 照着做一条这样的视频。
作者只公开了部分提示词。
Made with Opus 5.5, remotion y eleven labs. 145k tokens.
知识讲解0:59Opus 5.5 just one-shotted this explainer video for @sherwoodagent 🔥
Since I ran it within the context of our web app, it used existing components and branding to inform the design and used @Remotion skills for rendering
Kind of insane, haven't tried doing any video generation for months, but the latest models are making it easier to create content that is polished without heavy iteration
Prompt: "make a modern slick and punchy video for sherwood protocol. feel free to take branding or components from the landing page or app. the goal is to highlight how it enables agentic hedge funds, expl…
知识讲解0:30Claude Opus 5.5 on our AI coding benchmark: build a fully autonomous 3D water simulation from an empty repo - procedural mountains, rain, streams, lakes. TypeScript + Three.js, no physics engine.
One prompt, zero corrections, ~21 min. 23/23 tests green.
https://github.com/AiondaDotCom/ai-sim-benchmark