AI Agent Skills

[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling

把带时间戳的 narration.json 合成为中文解说音频。使用 MiMo TTS（mimo-v2.5-tts）或 Fish Audio（s2.1-pro-free）逐段生成语音， 按时间窗动态适配语速并处理响度；输入输出时间线上的旁白，产出 tts_segments 与 tts_meta.json。 旧版直接剪辑路径也可显式传入…

ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio

You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

Create motion for any robot through editing keyframe

A lightweight, flexible, and easy-to-use Python tool for generating and exporting CapCut drafts to build fully automated video editing/remix pipelines! Another similar p…

A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-rea…

Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cite…

Let's finetune video generation models!

Open-source, self-hosted alternative to NotebookLM. Chat with your documents, generate audio summaries, and ground AI in your own sources—built with Supabase and N8N on…

[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields

Automated daily tech briefing — multi-source collection → knowledge-base deduplication → AI summarization → TTS speech synthesis, generating MP3 audio briefings

把已确认的母题或文案转成可直接拍摄、录屏或交给视频工具制作的短视频方案，也支持在用户确认肖像与声音权利并完成平台手动上传后制作数字人视频。用于视频号、抖音、小红书视频和其他竖屏短视频的口播稿、前 3 秒钩子、分镜、字幕、录屏清单、封面、话题、BGM 建议、数字人制片包和发布文案。

Write short-form video scripts for TikTok, Instagram Reels, and YouTube Shorts that promote affiliate products with strong hooks, demos, and CTAs. Use this skill when th…

Custom ComfyUI node for generating videos with audio-visual identity based on a reference voice and image

[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion