Así puedes crear animaciones brutales con Claude Code
The video demonstrates how to use Claude Code with the Remotion skill to create professional animations for faceless YouTube channels. The creator walks through installation, basic usage, and shows how detailed prompts dramatically improve animation quality compared to vague ones.
Summary
The video opens by showcasing the monetization potential of faceless YouTube channels, citing an example channel with 1.8 million subscribers and 191 million views that could have earned between €400,000 and €800,000. The creator argues that Claude Code can be used to produce the kind of visuals these channels rely on, making the workflow significantly faster and more accessible.
The first major section covers the full installation process: creating a Claude account with a paid subscription, installing Visual Studio Code as the main working environment, installing Node.js to enable code execution, and installing Git for project management. The creator emphasizes using VS Code over the Claude Desktop app because it provides better visibility into files, folders, and the terminal simultaneously.
Next, the video covers installing Claude Code as an extension within VS Code and connecting it to the user's Claude account. An additional skill called Remotion is then installed via a terminal command, which acts as the bridge between Claude Code's React-based animations and actual video output. The creator recommends installing Remotion globally rather than per-project for convenience.
The practical demonstration begins with a simple prompt requesting a bar graph that counts from 0 to 125,000. The result is functional but visually basic, which the creator uses to make the point that Claude Code produces exactly what you ask for — no more, no less. The animation is previewed through the Remotion editor in a browser via a localhost server.
The video then escalates to a much more detailed prompt: a ranking of the top 10 highest-earning athletes, with names, sport, earnings figures, and a premium documentary-style aesthetic. The result is dramatically better — clean, well-structured, and closer to broadcast quality. The creator attributes the quality jump entirely to the specificity of the prompt, recommending that viewers use other LLMs like ChatGPT or Gemini to help write detailed prompts if needed.
Finally, the creator demonstrates iterative refinement — converting horizontal bars to vertical ones, narrowing the ranking to a top-3 podium format with cinematic card-style visuals, and even generating a narrative timeline animation about Nike vs. Adidas. The video concludes by showing how finished animations can be rendered and exported directly from Remotion for use in any video editor.
Key Insights
- The creator argues that a faceless YouTube channel with 191 million views could have generated between €400,000 and €800,000, and claims many of those visual resources can now be built much more easily with Claude Code.
- The creator explains that Claude Code uses React web technology to build animations and Remotion converts them into video, describing it as 'a completely different way of working, but also much faster' than traditional video editors.
- The creator demonstrates that a vague prompt produces a functional but generic result, arguing that 'Claude Code does exactly what you ask it to, but it won't guess the style, animation type, or design you have in mind.'
- The creator claims the key to professional-quality output is giving Claude Code not just what you want, but also how it should look, what exact data to use, what visual style is desired, and what feeling it should convey — and recommends using other LLMs to help write detailed prompts.
- The creator highlights iterative refinement as a core advantage, stating 'you don't have to redo everything from scratch' — instead, you can change format, structure, or style by simply continuing the conversation with Claude Code from an already-working base.
Topics
Transcript
[0:00] In this video I'm going to show you how to use Cloud Code to create animations for your YouTube videos or for any social network. For example, look, this channel here has over 1.8 million subscribers and over 191 million views without showing its face. It's a completely faceless channel. A Faceless channel is a type of channel where the creator never appears on camera and all content is based on voice, images, clips, or animations. And [0:30] we can use cloud code to start creating visuals and animations along these lines. In fact, based on my experience with YouTube and if we do some quick calculations, YouTube usually pays between €2 and €4 for every 1000 views. So…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Migue Baena IA
Cómo aprender por tu cuenta y volverte imparable con IA
This tutorial demonstrates how to use Gemini Notebook (formerly Notebook LM) to self-teach any skill by curating personal learning sources and converting them into multiple study formats. The four-step process involves selecting quality materials, studying them through different media, teaching the content to others, and integrating learning into daily routines.
Tienes que probar esto antes de crear tus videos con IA 🎬
A new AI video creation tool called 3D Builder within Topw Film Studio allows creators to pre-visualize and plan movie scenes by building interactive 3D environments, positioning characters and objects, controlling camera movements, and reviewing animations before final video generation.
No elijas entre Claude y Codex: úsalos juntos 🤝🏻
The video proposes using Claude and Codex together rather than choosing one over the other to maximize their respective strengths. Claude handles problem analysis and task delegation while Codex executes code generation, allowing users to work around individual API rate limits and leverage complementary capabilities.
Cómo usar Claude mejor que el 99% de la gente
A comprehensive guide to using Claude AI effectively, covering account setup with context import, model selection and reasoning levels, proper prompting techniques, projects and skills for organizing work, and advanced features like Cowork for delegated tasks and Code for building applications.
El archivo de GitHub que deberías de conocer 👀
Anthropic has published a detailed GitHub repository containing a 275,000+ character PRD with nearly 8,000 lines of instructions for one of their models, including specifications on what to do, avoid, and how to use tools. The key value lies not in copying the content but in studying its structure and learning how it organizes rules and defines tool usage for prompt engineering applications.