Video & Animation

Write HTML. Render video. Built for agents.

Build programmatic UIKit apps with production-ready patterns for views, navigation, animation, architecture, and data flow

Build Ozor AI video prompts and skills for product launches, ads, explainers, and more

Create and manage Flowith canvas work from the CLI for images, text, video, agent runs, and semantic recall

Manage Flowith canvases from the CLI to create, read, batch, and recall AI-generated nodes, images, text, video, and agent outputs

Browse curated DESIGN.md files for developer sites and copy proven layouts into your project for AI-driven, pixel-perfect page builds

Provide structured patterns for AI agents to write production-grade TypeScript, React, and Next.js code.

Open-source agent skills + Claude Code plugin for Tolstoy — create marketing videos/images and remix your library, via the Tolstoy MCP.

TRTC AI Integration Assistant - helps developers integrate Tencent Real-Time Communication SDKs (Chat, Call, RTC Engine, Live, Conference) across Web, Android, iOS, Flutter, and Electron.

Hub-and-spoke agent-skill clusters, one per stack (Astro·GSAP·Remotion, Tauri, …). Installable via skills.sh.

A Simple Baseline for Video World Models with Memory

14 Claude Code skills for video, content publishing & knowledge management — DaVinci subs, WeChat, Obsidian, GEO.

🎙️ Automate podcasting with skills: download YouTube videos, process audio, and manage content efficiently—all in one comprehensive toolkit.

Visualize AI chat traits to build a clear portrait of your style and tone

Automate AI short video production with a semantic-aligned pipeline for agents, from script generation to final render, with human-in-the-loop checkpoints.

Free local-first agent skill for video clipping, offline subtitles, portrait reframing, EDL, and FFmpeg export

大瑀创意科技 AI Skill — MCP 营销服务查询 | AI Marketing Service Skill by DY Creative&Tech (Hangzhou) — MCP Server for Douyin, Xiaohongshu, AIGC marketing

Turn knowledge docs into interactive courseware — with narration, quizzes, 3D scenes, and embedded assessment. Forked from web-video-presentation.

Enables multi-modal orchestrators to automate step-by-step upscaling, frame interpolations, and video enhancement passes.

Audio generation research framework providing music editing agents with deep conceptual generation structures over raw sound fields.

Advanced text-to-speech tools giving video creation agents automated control over structural voice emphasis and matching rules.

Transformer-based audio model interfaces allowing sound agents to generate music, sound effects, and rich speech narratives.

Instant voice cloning pipeline extensions allowing conversational agents to clone accent styles dynamically via brief audio prompts.

Frame processing logic computing structural object trajectories inside continuous security video tracking systems.