33 boosters for "eos" — open source, verified from GitHub, ready to install
Sora enables Claude Code users to generate, remix, and manage AI videos directly through OpenAI's video API. Developers building products with video content (demos, marketing, UI mocks) benefit from integrated video generation workflows.
"name": "claude-video-vision", "description": "Give Claude the ability to watch and understand videos — extracts frames and audio for full video perception", "name": "Jordan Vasconcelos",
Frontmatter fields above are primarily for Claude Code / OpenClaw. author: Agents365-ai category: Content Creation
This MCP server enables Claude to directly download and access YouTube video transcripts, making it easy for developers to integrate transcript extraction into AI workflows. It benefits content researchers, developers building transcript-based applications, and anyone needing programmatic access to YouTube video text.
YouTube Audio is a browser extension that strips video from YouTube streams, preserving only audio to save battery and bandwidth. It's useful for users who consume YouTube content primarily for audio (music, podcasts, lectures) and want to reduce data usage.
DyNote 是面向 Codex 这类 Agent 的抖音学习工具，不是一次性摘要器。核心原则是“数据资产先行，学习笔记后置”：先把字幕/转写、评论、元数据和 AI 快读沉淀为可复用资产，再按用户需求生成可追溯的学习笔记、总结和写作材料。默认目标不是字幕工程文件，而是先落一份原始数据包：、、、、、、，并用 归档可复用资产。默认把独立字幕轨或本地自动语音识别转写当作事实主干；当转写密度低、任务需要画面理解或用户只要快速筛选时，再用已登录抖音网页版的“问AI / 识别画面”补充，豆包只作为抖音 AI 不可用时的备用快读或待核验假设。 联网或登录态操作必须先使用 。不要读取、复制或打印 Cooki
"name": "manim-skill", "description": "Claude Code Skill for creating mathematical animations using Manim Community Edition. Plan, code, render, and iterate on 3Blue1Brown-style videos.", "name": "Yusuke Miyashita"
Help users slim down their iPhone storage. Scan media, back up files to the computer, delete verified files from the device, and guide users through the steps only Apple allows on the phone itself. Use this skill whenever the user says: "my iPhone is full", "clean up my iPhone", "free up iPhone stor
Production-grade geospatial workflows with an open-first stack and pragmatic hosted/SaaS choices when global scale, latency, SLA, or data quality makes local processing a poor fit. Cloud-native by default: STAC for discovery, GeoParquet + COG + PMTiles for storage, DuckDB and PostGIS for compute, Ma
1. Update README.md - Minimal info only, focus on quick start + links to GitHub Pages 2. Update src/CONFIG_README.md - Essential configuration overview + links to full docs 3. Update GitHub Pages ( folder) - Complete, detailed documentation
Automates the discovery and summarization of AI-related YouTube content from subscribed channels by fetching transcripts and generating Markdown reports. Useful for researchers, learners, and content curators who want to stay updated on AI topics without manually watching videos.
Automates the process of discovering, transcribing, and summarizing AI-related YouTube videos from subscribed channels into organized Markdown reports. Ideal for AI researchers, developers, and enthusiasts who want to stay current with YouTube AI content without manual effort.
The most powerful personal brand camera move. Communicates: "this person is worth getting closer to." Creates authenticity by mimicking doc-style camera work. Shows the subject from multiple angles, communicating confidence.
Traditional testimonials fail because they're static talking heads in flat lighting. Cinematic social proof makes viewers feel the transformation. Show the result first, the emotion second, the person third. The first two seconds determine whether the viewer stays. Every testimonial video needs an i
Transform podcast audio into cinematic visual content using Seedance 2.0 on Higgsfield. This skill produces video prompts that replace static audiograms with storytelling-driven visual experiences built entirely from constructed imagery. The hook is the opening frame that stops the scroll. It must c
When generating a prompt, collect or infer: Seedance 2.0 prompt structure: Each prompt block should be 15–25 lines covering: scene, camera, lighting, timing breakdown, motion notes, and sound direction.
A complete system for crafting Seedance 2.0 prompts on Higgsfield that feature AI avatars, digital personas, virtual presenters, and synthetic characters as the primary subject. This skill covers everything from photorealistic digital humans to stylized 3D characters, including hook patterns, enviro
The first two seconds determine whether a viewer stops scrolling. These patterns open with immediate visual authority. Luxury camera work operates within a narrow, controlled vocabulary. No exceptions. The most used luxury camera move. Camera travels toward subject at 0.1x–0.3x of normal speed. Tota
Turn social media paper recommendations into actionable research items. Use platform-specific tools to fetch the full content: From the extracted content, identify all referenced papers:
"description": "Generate images, videos, and music using 600+ Fal.ai models. Supports Flux, SDXL, Kling Video, and more.", "version": "1.14.0", "name": "Raveen Beemsingh",
Pooch enables reliable downloading, caching, and verification of geoscience datasets with automatic integrity checks and multi-source fallback support. Essential for researchers and developers working with large scientific data files who need reproducible, efficient data workflows.
Analyzes videos (YouTube, GIFs, screen recordings) using Gemini to extract step-by-step build instructions and technical specifications for Claude. Ideal for developers who want to understand, clone, or reverse-engineer UI components and products from video demos.
A Cursor rules booster that enables developers to build iOS apps for translating burned-in video subtitles using Vision OCR and Apple's translation API. Useful for developers working with multilingual video content and social media platforms like RedNote.
