Agent Skill
Quantizing Models Bitsandbytes
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 infere…
DevOps & Cloud
Docker, CI/CD, cloud, Linux and Git.
404 prompts
Agent Skill
Optimizing Attention Flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 token…
Agent Skill
Sparse Autoencoder Training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when disco…
Agent Skill
Mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
Agent Skill
Rwkv Architecture
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 proje…
Agent Skill
Tensorrt LLM
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x f…
Agent Skill
Serving LLMs Vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or…
Agent Skill
Lambda Labs Gpu Cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or hi…
Agent Skill
Modal Serverless Gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running…
Agent Skill
Skypilot Multi Cloud Orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instan…
Agent Skill
Speculative Decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), re…
Agent Skill
Nemo Evaluator SDK
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on loca…
Agent Skill
Training LLMs Megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum…
Agent Skill
Model Pruning
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with m…
Text
Generate Linear Work Log
Generate Linear Work Log You are tasked with generating a technical work log comment for a Linear issue based on recent git commits. Instructions 1. Check Linear MCP Ava…
Text
Git Status Command
Git Status Command Show detailed git repository status Command originally created by IndyDevDan (YouTube: https://www.youtube.com/@indydevdan) / DislerH (GitHub: https:/…
Text
Clean Branches Command
Clean Branches Command Clean up merged and stale git branches Instructions Follow this systematic approach to clean up git branches: $ARGUMENTS 1. Repository State Analy…
Text
Context Prime
Read README.md, THEN run git ls-files grep -v -f (sed 's ^ ^ ; s $ / ' .cursorignore psub) to understand the context of the project
Text
Standup Report
Generate comprehensive daily standup reports with team activity analysis and progress tracking
Text
Sync Automation Setup
Setup comprehensive automated synchronization workflows with monitoring and CI/CD integration
Text
Sync Migration Assistant
Comprehensive migration assistant for large-scale GitHub-Linear data transitions with validation and rollback
Text
Setup CI/CD Pipeline
Setup comprehensive CI/CD pipeline with automated testing, deployment, and monitoring
Text
Setup Development Environment
Setup comprehensive development environment with tools, configurations, and workflows
Text
Setup Docker Containers
Setup Docker containerization with multi-stage builds and development workflows