80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
running-python
by benchflow-ai
Runs Python scripts and manages projects using uv. Use when asked to run a python script, execute python code, run pytes...
pytorch-core
by benchflow-ai
Core PyTorch fundamentals including tensor operations, autograd, nn.Module architecture, and training loop orchestration...
moai-lang-cpp
by benchflow-ai
Modern C++ (C++23/C++20) development specialist covering RAII, smart pointers, concepts, ranges, modules, and CMake. Use...
numpy-ufuncs
by benchflow-ai
Universal functions (ufuncs) for vectorization, including reductions, in-place operations, and custom Python-function wr...
polyglot-integration
by benchflow-ai
Integrate multiple programming languages using FFI, native bindings, gRPC, or language bridges. Use when combining stren...
pytorch
by benchflow-ai
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pip...
pytorch-distributed
by benchflow-ai
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers m...
numpy-core
by benchflow-ai
Fundamental NumPy operations including ndarray creation, dtypes, shape manipulation, and basic operations with a focus o...
rust-ffi
by benchflow-ai
Microsoft Pragmatic Rust FFI Guidelines. Use when working with C/C++ interop, creating cdylib, writing unsafe FFI code,...
huggingface-tokenizers
by benchflow-ai
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports...
ml-inference-optimization
by benchflow-ai
ML inference latency optimization, model compression, distillation, caching strategies, and edge deployment patterns. Us...
llm-serving-patterns
by benchflow-ai
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies...
google-gemini-embeddings
by benchflow-ai
Build RAG systems, semantic search, and document clustering with Gemini embeddings API (gemini-embedding-001). Generate...
gemini-video-understandin...
by benchflow-ai
Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions...
transformers
by benchflow-ai
Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFa...
sentence-transformers
by benchflow-ai
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic simi...
embedding-strategies
by benchflow-ai
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, imple...
cost-latency-optimizer
by benchflow-ai
Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provi...
serving-llms-vllm
by benchflow-ai
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM...
pdf-processing
by benchflow-ai
Invoke this skill BEFORE implementing any text extraction/parsing logic to learn how to use LlamaParse to process any do...
funsloth-check
by benchflow-ai
Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchi...
hfskill
by benchflow-ai
Comprehensive toolkit for interacting with Hugging Face Spaces. Use this skill when working with Hugging Face Spaces - l...
nanogpt
by benchflow-ai
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning...
backend-api
by benchflow-ai
Design and implement RESTful API endpoints following REST principles with consistent naming conventions, proper HTTP met...