Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with...
AI & LLM
LLM integrations, prompt engineering, and AI orchestration
8,093 技能
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert...
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for...
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16×...
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation,...
Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when...
Prepares meeting materials by gathering context from Notion, enriching with Claude research, and creating both an...
Turns product or tech specs into concrete Notion tasks that Claude code can implement. Breaks down spec pages into...
|
|
|
|
|
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models...
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local...
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting...
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This...
This skill should be used when working with reinforcement learning tasks including high-performance RL training,...
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical...
Laboratory automation toolkit for controlling liquid handlers, plate readers, pumps, heater shakers, incubators,...
Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison,...
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks...
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits,...
Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to PyPI....