Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterbox (classic and multilingual), F5-TTS, Higgs Audio 2, 3, and VibeVoice with unlimited text length, SRT timing, Character support, and many audio tools

A long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post", "essay", or "case study".

A collection of reusable agent skills for Dart and Flutter development, following the Agent Skills standard.

Use when reviewing a PR, API, IPC channel, endpoint, parameter, type, config, or architectural extension point that adds or expands shared surface area, especially when consumers are absent, exports are unused or speculative, existing consumers are hack-heavy, forward compatibility is claimed, or multiple similar APIs may express one demand.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality gate.

We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

AI Agent开发进阶笔记，包含可运行的零依赖Node.js代码，讲解coding agent内部机制。