80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
adk-rag-agent
by cuba6112
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing docume...
unsloth-qlora
by cuba6112
Advanced 4-bit quantization techniques using Unsloth and BitsAndBytes for extreme VRAM efficiency (triggers: QLoRA, 4-bi...
numpy-set-ops
by cuba6112
Set-theoretic operations for finding unique elements, membership testing, and array intersections. Triggers: unique, isi...
git-commit-helper
by cuba6112
Adherence to Conventional Commits and efficient Git history management using types, scopes, and advanced commit tools li...
structured-outputs
by cuba6112
Techniques for ensuring LLM responses adhere to strict JSON schemas, utilizing Pydantic models, JSON mode, and schema-ba...
unsloth-inference
by cuba6112
Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: infere...
pytorch-core
by cuba6112
Core PyTorch fundamentals including tensor operations, autograd, nn.Module architecture, and training loop orchestration...
ollama-rag
by cuba6112
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder...
numpy-indexing
by cuba6112
Advanced indexing techniques including slicing, fancy indexing, and boolean masks, along with memory implications of vie...
pytest-patterns
by cuba6112
Advanced Python testing strategies with Pytest, covering fixtures, matrix testing with parametrization, and async test a...
github
by cuba6112
Automation of GitHub tasks using the gh CLI and REST API. Includes pagination strategies, payload construction, and rate...
unsloth-core
by cuba6112
Core fundamentals of Unsloth for fast LLM fine-tuning, covering FastLanguageModel setup, optimized gradient checkpointin...
fastapi-patterns
by cuba6112
Advanced FastAPI patterns including hierarchical dependency injection, background task management, and type-safe depende...
numpy-sorting
by cuba6112
Sorting and searching algorithms including O(n) partitioning, binary search, and hierarchical multi-key sorting. Trigger...
unsloth-orpo
by cuba6112
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization,...
pytorch-quantization
by cuba6112
Techniques for model size reduction and inference acceleration using INT8 quantization, including Post-Training Quantiza...
unsloth-gguf
by cuba6112
Exporting fine-tuned models to GGUF format for deployment in llama.cpp, Ollama, and local serving tools. Triggers: gguf,...
agentic-patterns
by cuba6112
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool rout...
unsloth-models
by cuba6112
Guidance on selecting and configuring supported model architectures like Llama 4, DeepSeek-R1, and Qwen3. Triggers: llam...
tool-calling
by cuba6112
Define and run tool-calling patterns for LLMs (schema design, call loops, validation, parallel calls). Use when building...
torch-compile
by cuba6112
Optimize PyTorch with torch.compile (TorchDynamo/Inductor), focusing on compile overhead, graph breaks, and benchmark me...
unsloth-fft
by cuba6112
Performing full fine-tuning (FFT) in Unsloth with 100% exact weight updates and optimized gradient checkpointing. Trigge...
pytorch-onnx
by cuba6112
Exporting PyTorch models to ONNX format for cross-platform deployment. Includes handling dynamic axes, graph optimizatio...
pytorch-geometric
by cuba6112
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large...