GitHub
polyglot-integration
Integrate multiple programming languages using FFI, native bindings, gRPC, or language bridges. Use when combining strengths of different languages or integrating legacy systems.
☆ 620View skill
benchflow-ai AI Skills
GitHub ↗Browse published AI skills maintained by benchflow-ai. Compare skill descriptions and follow each source repository for setup instructions.
Author statistics
Indexed skills
349Repository stars across indexed skills
183,468Repository forks
66,973Average repository stars per indexed skill
526Repository stars may repeat across skills from the same repository.
Popular categories
Recent indexing activity
Browse skills
GitHub
pytorch
Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch...
☆ 620View skill
GitHub
pytorch-distributed
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distrib...
☆ 620View skill
GitHub
numpy-core
Fundamental NumPy operations including ndarray creation, dtypes, shape manipulation, and basic operations with a focus on memory alignment and data views. Triggers: numpy, ndarray, dtype, reshape, memory alignm...
☆ 620View skill
GitHub
rust-ffi
Microsoft Pragmatic Rust FFI Guidelines. Use when working with C/C++ interop, creating cdylib, writing unsafe FFI code, or multi-DLL Rust projects.
☆ 620View skill
GitHub
huggingface-tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in
☆ 620View skill
GitHub
ml-inference-optimization
ML inference latency optimization, model compression, distillation, caching strategies, and edge deployment patterns. Use when optimizing inference performance, reducing model size, or deploying ML at the edge.
☆ 620View skill
GitHub
llm-serving-patterns
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns. Use when designing LLM serving infrastructure, optimizi...
☆ 620View skill
GitHub
google-gemini-embeddings
Build RAG systems, semantic search, and document clustering with Gemini embeddings API (gemini-embedding-001). Generate 768-3072 dimension embeddings for vector search, integrate with Cloudflare Vectorize, and...
☆ 620View skill
GitHub
gemini-video-understanding
Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions, reference timestamps, clip videos, and process YouTube URLs. Supports 9 video formats, m...
☆ 620View skill
GitHub
transformers
Work with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing...
☆ 620View skill
GitHub
sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal...
☆ 620View skill
GitHub
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
☆ 620View skill
GitHub
cost-latency-optimizer
Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost re...
☆ 620View skill
GitHub
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 serving models with limited GPU memory....
☆ 620View skill
GitHub
pdf-processing
Invoke this skill BEFORE implementing any text extraction/parsing logic to learn how to use LlamaParse to process any document accurately. Requires llama_cloud_services package and LLAMA_CLOUD_API_KEY as an env...
☆ 620View skill
GitHub
funsloth-check
Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.
☆ 620View skill
GitHub
hfskill
Comprehensive toolkit for interacting with Hugging Face Spaces. Use this skill when working with Hugging Face Spaces - listing spaces, retrieving space information, managing space runtime (restart/pause), check...
☆ 620View skill
GitHub
nanogpt
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch....
☆ 620View skill
GitHub
backend-api
Design and implement RESTful API endpoints following REST principles with consistent naming conventions, proper HTTP methods, versioning strategies, and appropriate status codes. Use this skill when creating ne...
☆ 619View skill
GitHub
python-coder
Modern Python 3.12+ development with uv, ruff, pydantic, FastAPI, async patterns, and production-ready practices.
☆ 618View skill
GitHub
nginx-sites-available
Generates nginx-sites-available-default configuration file for serving the Vue application on Debian/Ubuntu-based nginx installations.
☆ 618View skill
GitHub
nginx-configuration
Configure Nginx web server for high-performance reverse proxy, load balancing, SSL/TLS, caching, and API gateway functionality.
☆ 618View skill
GitHub
react-best-practices
**IMPORTANT**: Any change to React or Next.js code must read through this skill first. React and Next.js guidelines from Vercel Engineering covering visual instability, layout shifts, CLS, flickering, hydration...
☆ 618View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.