AI Agent Skills

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, i…

KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019

A full attention mechanism and transformer in pure go.

A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Replication of simple CV Projects including attention, classification, detection, keypoint detection, etc.

BertViz: Visualize Attention in Transformer Models

Go实现的Trojan代理，支持多路复用/路由功能/CDN中转/Shadowsocks混淆插件，多平台，无依赖。A Trojan proxy written in Go. An unidentifiable mechanism that helps you bypass GFW. https://p4gefau1t.github.io/…

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

It is open source ebook about TensorFlow kernel and implementation mechanism.

Create, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python (matplotlib/seaborn) or R (ggplot

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastT…

This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-patt…

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention me…

This skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\", \"orchestrator worker context\", \"latent brief…

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching.…