모든 Claude 스킬 탐색
AI 에이전트 기능을 확장하는 Claude 스킬의 전체 컬렉션을 살펴보세요.
Pinecone Vector Database Integration
Manages high-performance vector search and storage for production RAG and AI applications using Pinecone's serverless infrastructure.
CLIP Vision-Language Model
Enables zero-shot image classification and semantic image search by connecting visual concepts with natural language.
nnsight Model Interpretability
Interprets and manipulates neural network internals for any PyTorch model, including massive foundation models via remote execution.
DSPy Declarative AI Programming
Builds complex AI systems using Stanford's declarative programming framework to optimize prompts and create modular RAG systems automatically.
vLLM High-Performance Inference Serving
Serves Large Language Models with maximum throughput and efficiency using vLLM's PagedAttention and continuous batching.
LlamaGuard Content Moderation
Moderates and filters AI inputs and outputs using Meta's specialized safety alignment models to prevent harmful content generation and ensure compliance.
Claude Skill Reviewer
Reviews and optimizes Claude Code skills against official best practices to ensure high quality, security, and discoverability.
LLaVA Multimodal Assistant
Enables advanced vision-language capabilities for image understanding, multi-turn visual conversations, and document analysis.
AudioCraft AI Generation
Generates high-fidelity music and sound effects from text descriptions using Meta's AudioCraft framework.
Unsloth Fine-Tuning
Accelerates LLM fine-tuning workflows with Unsloth to achieve up to 5x faster training speeds and 80% reduced memory consumption.
Flash Attention Optimization
Optimizes Transformer models using Flash Attention to achieve significant speedups and memory reductions during training and inference.
HuggingFace Accelerate Distributed Training
Simplifies PyTorch distributed training by providing a unified API for DDP, DeepSpeed, and FSDP with minimal code changes.
GitHub Contributor Strategy
Guides developers through the strategic process of contributing to open-source projects and building a professional GitHub reputation.
GRPO RL Fine-Tuning
Implements Group Relative Policy Optimization (GRPO) using the TRL library to enhance model reasoning and structured output capabilities.
LlamaIndex RAG Framework
Connects LLMs to private data sources through advanced document ingestion, vector indexing, and retrieval-augmented generation (RAG) pipelines.
LLM Guidance & Constrained Generation
Enforces structured LLM outputs using regex and grammars to guarantee valid JSON, XML, and code generation.
Twitter Reader
Fetches Twitter/X post content and metadata into clean Markdown format using the Jina.ai API to bypass JavaScript restrictions.
Segment Anything Model (SAM)
Implements Meta AI's foundation model for high-precision zero-shot image segmentation using points, boxes, and masks.
bitsandbytes LLM Quantization
Quantizes Large Language Models to 4-bit or 8-bit formats to reduce GPU memory usage by up to 75% with minimal accuracy loss.
SAELens: Mechanistic Interpretability
Decomposes complex neural network activations into sparse, interpretable features to understand and steer model behavior.
LangSmith LLM Observability
Integrates comprehensive tracing, evaluation, and monitoring tools to debug and optimize Large Language Model (LLM) applications.
Chroma Vector DB
Manages local and server-based vector embeddings for RAG and semantic search applications.
LLM Model Pruning
Compresses Large Language Models using advanced techniques like Wanda and SparseGPT to reduce memory footprint and accelerate inference speeds.
TransformerLens Mechanistic Interpretability
Facilitates mechanistic interpretability research by providing tools to inspect, cache, and manipulate transformer model activations via HookPoints.
Mamba Architecture & SSM Implementation
Implements and optimizes Mamba-based Selective State Space Models for high-efficiency sequence modeling and long-context AI research.
BLIP-2 Multimodal Vision
Integrates Salesforce's BLIP-2 framework to enable advanced image captioning, visual question answering, and multimodal reasoning within AI workflows.
MoE Training (Mixture of Experts)
Implements and optimizes Mixture of Experts (MoE) architectures to scale model capacity while reducing training and inference costs.
NeMo Curator - GPU Data Curation
Curates high-quality datasets for LLM training using GPU-accelerated deduplication, filtering, and PII redaction.
SentencePiece Tokenizer
Implements language-independent subword tokenization using BPE and Unigram algorithms for advanced AI model development.
Modal Serverless GPU
Deploys and manages machine learning workloads on serverless GPU infrastructure using Python-native configurations.
Scroll for more results...