davila7/claude-code-templates

High-performance serving framework for LLMs and VLMs with RadixAttention for automatic prefix caching.

Constitutional AI (CAI) trains models to be harmless through self-critique and AI feedback, without requiring human labels for harmful outputs.

NetworkX is a Python package for creating, manipulating, and analyzing complex networks and graphs. Use this skill when working with network or graph data structures, including social networks, biological networks, transportation systems, citation networks, knowledge graphs, or any system involving relationships...

Comprehensive guide to running ML workloads across clouds with automatic cost optimization using SkyPilot.

Generate professional clinical decision support (CDS) documents for pharmaceutical companies, clinical researchers, and medical decision-makers. This skill specializes in analytical, evidence-based documents that inform treatment strategies and drug development:

Flash Attention provides 2-4x speedup and 10-20x memory reduction for transformer attention through IO-aware tiling and recomputation.

TransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models. Created by Neel Nanda and maintained by Bryce Meyer, it provides clean interfaces to inspect and manipulate model internals via HookPoints on every activation.

OpenAI's model that understands images from natural language.

Comprehensive guide to running ML workloads on Lambda Labs GPU cloud with on-demand instances and 1-Click Clusters.

NeMo Guardrails adds programmable safety rails to LLM applications at runtime.

bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss.

SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.

LitGPT provides 20+ pretrained LLM implementations with clean, readable code and production-ready training workflows.

ClinicalTrials.gov is a comprehensive registry of clinical studies conducted worldwide, maintained by the U.S. National Library of Medicine. Access API v2 to search for trials, retrieve detailed study information, filter by various criteria, and export data for analysis. The API is public (no authentication required)...

Treatment plan writing is the systematic documentation of clinical care strategies designed to address patient health conditions through evidence-based interventions, measurable goals, and structured follow-up. This skill provides comprehensive LaTeX templates and validation tools for creating concise, focused...

PyHealth is a comprehensive Python library for healthcare AI that provides specialized tools, models, and datasets for clinical machine learning. Use this skill when developing healthcare prediction models, processing clinical data, working with medical coding systems, or deploying AI solutions in healthcare settings.

PyMC is a Python library for Bayesian modeling and probabilistic programming. Build, fit, validate, and compare Bayesian models using PyMC's modern API (version 5.x+), including hierarchical models, MCMC sampling (NUTS), variational inference, and model comparison (LOO, WAIC).

pyvene is Stanford NLP's library for performing causal interventions on PyTorch models. It provides a declarative, dict-based framework for activation patching, causal tracing, and interchange intervention training - making intervention experiments reproducible and shareable.

GeoPandas extends pandas to enable spatial operations on geometric types. It combines the capabilities of pandas and shapely for geospatial data analysis.

Expert-level guidance for implementing Group Relative Policy Optimization (GRPO) using the Transformer Reinforcement Learning (TRL) library. This skill provides battle-tested patterns, critical insights, and production-ready workflows for fine-tuning language models with custom reward functions.

Mamba is a state-space model architecture achieving O(n) linear complexity for sequence modeling.

Open-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiments, and real-time monitoring.

Add official Railway database services. These are maintained templates with pre-configured volumes, networking, and connection variables.

scikit-survival is a Python library for survival analysis built on top of scikit-learn. It provides specialized tools for time-to-event analysis, handling the unique challenge of censored data where some observations are only partially known.