Search Results for "support"
ray-data
★ 62Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
huggingface-accelerate
★ 62Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
quantizing-models-bitsandbytes
★ 62Quantizes 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 inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
optimizing-attention-flash
★ 62Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
evaluating-llms-harness
★ 62Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
llama-cpp
★ 62Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
serving-llms-vllm
★ 62Serves 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. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
langchain
★ 62Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
llamaindex
★ 62Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
faiss
★ 62Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
sentence-transformers
★ 62Framework 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 models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
llava
★ 62Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.
whisper
★ 62OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
json-parser
★ 56Parse and validate JSON data with schema support
file-reference-skill
★ 56Example skill demonstrating secure file reference resolution with supporting files
composewebview-development
★ 52Builds, tests, and formats ComposeWebView multiplatform library. Handles Android, iOS, Desktop (JVM), and Web (JS) platforms. Use when building, testing, running Spotless formatting, or checking platform-specific code. Supports expect/actual pattern workflows.
vitest-runner
★ 51Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.
pytest-runner
★ 51Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.
Frequently Asked Questions
What is a Claude Skill?
It is a modular, protocol-based instruction set that enables Claude to perform specific tasks autonomously and efficiently.
How is this different from regular prompts?
Skills use the official Anthropic protocol for better token efficiency and automatic triggering compared to static prompts.
Does it support the new Claude Code CLI?
Yes, we provide specialized one-click installation commands designed specifically for Claude Code and OpenCode.
Can I use these skills in Cursor?
Absolutely, our library is fully compatible with popular IDEs and extensions including Cursor, Codex, and AntiGravity.
Are the skills on the website free to use?
Most skills in our 90,000+ database are free and open-source for the community to download and deploy.
How can I contribute my own skills?
Developers can easily share their work by submitting their own skill repositories through our community portal.