Guidance for asking clarifying questions when user requests are ambiguous, have multiple valid approaches, or require critical decisions. Use when implementation choices exist that could...

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building...

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat),...

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows,...

フロントエンドUIデザインを洗練された独自性のあるスタイルで生成します。ランディングページ、ダッシュボード、Webアプリケーションのデザイン、UIコンポーネント作成時に使用してください。「AIっぽい」汎用デザインを避け、プロフェッショナルで記憶に残るUIを実現します。

扫描目录识别所有类型发票（交通、住宿、餐饮等），提取关键信息并生成分类统计报告

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive...

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse...

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting,...

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M...

Plan and coordinate multi-agent bead execution. Use when starting a new epic, assigning tracks to agents, or monitoring parallel work progress.

Interact with a web browser. Can start a browser, connect to it, evaluate JavaScript, make screenshots, read console logs and let the user select DOM elements. Use when interacting with unknown...

Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterprise AI engineering lens. Use when user provides URL/document for AI/ML...

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with...

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or...

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track...

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4,...