obsidian
Manage prompts in your Obsidian vault. Use for saving, listing, and loading reusable prompts. Triggers on /obsidian commands, Obsidian vault operations, or prompt management requests.
ginx-skill
Develop HTTP APIs, middleware, error codes, and i18n strings using the ginx framework conventions. Use when creating or modifying APIs in apis/, defining error codes, adding i18n strings, or when the user asks to follow project conventions for HTTP endpoints, routes, middleware, or error handling.
festival-operator
This skill should be used when the user asks about "festival operations", "event management", "vendor management", "lost and found procedures", "security protocols", "customer service at events", "handling difficult customers", "festival emergencies", "marketing communications", or discusses managing festivals, winter events, or public gatherings.
powershell-skill
Execute PowerShell commands on Windows systems with security constraints
modern-doc
>
morpho-solana-frontend
Build production-ready frontend for Morpho Blue lending protocol on Solana. Covers all 26 program instructions across supply/borrow, flash loans, liquidations, authorization, and admin features. Uses Next.js 14, Anchor client, Jupiter wallet adapter, and Kamino-style UI/UX. Integrates with morpho-solana-builder skill for contract understanding.
PDF Manipulation
Enables Claude to read, manipulate, and fill out PDF forms
festival-operations
Expert knowledge for running winter festival operations (Security, Marketing, CX, Lost & Found).
unsloth-tts
Fine-tuning Text-to-Speech (TTS) models with Unsloth for voice cloning and synthetic speech (triggers: TTS, text-to-speech, voice cloning, Orpheus-TTS, audio fine-tuning, speech synthesis).
unsloth-stt
Fine-tuning Speech-to-Text models like Whisper using Unsloth's optimized LoRA pipeline. Triggers: stt, whisper, transcription, audio fine-tuning, speech-to-text, audio normalization.
unsloth-quantization
Utilizing Dynamic 4-bit quantization, FP8 training, and 8-bit optimizers to minimize VRAM usage without sacrificing accuracy. Triggers: quantization, dynamic 4-bit, fp8, bitsandbytes, adamw_8bit, qat.
unsloth-sft
Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation with triggers like sft, instruction tuning, chat templates, sharegpt, alpaca, conversation_extension, and SFTTrainer.
torchserve
Model serving engine for PyTorch. Focuses on MAR packaging, custom handlers for preprocessing/inference, and management of multi-GPU worker scaling. (torchserve, mar-file, handler, basehandler, model-archiver, inference-api)
torchtext
Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, regextokenizer, nlp-pipeline)
vector-databases
Design vector database ingestion and retrieval pipelines (points + payloads, filtered similarity search, multi-stage hybrid retrieval, index maintenance). Use when building RAG/vector search flows or debugging retrieval quality; triggers: vector database, RAG, embeddings, hybrid search, filtered search, Qdrant, Weaviate, Chroma.
unsloth-vision
Fine-tuning multimodal vision-language models (Llama 3.2 Vision, Qwen2.5 VL) using optimized vision layers (triggers: vision models, multimodal, Llama 3.2 Vision, Qwen2.5 VL, UnslothVisionDataCollator, finetune_vision_layers).
torchvision
Computer vision library for PyTorch featuring pretrained models, advanced image transforms (v2), and utilities for handling complex data types like bounding boxes and masks. (torchvision, transforms, tvtensor, resnet, cutmix, mixup, pretrained models, vision transforms)
unsloth-core
Core fundamentals of Unsloth for fast LLM fine-tuning, covering FastLanguageModel setup, optimized gradient checkpointing, and native inference acceleration (triggers: unsloth, FastLanguageModel, from_pretrained, get_peft_model, for_inference, gradient checkpointing).
unsloth-cpt
Strategies for continued pretraining and domain adaptation in Unsloth (triggers: continued pretraining, CPT, domain adaptation, lm_head, embed_tokens, rsLoRA, embedding_learning_rate).
unsloth-datasets
Standardizing and formatting datasets for Unsloth, including chat template conversion and synthetic data generation (triggers: chat templates, ShareGPT, Alpaca, conversation_extension, add_new_tokens, standardize_sharegpt, formatting_prompts_func).
unsloth-dpo
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
unsloth-fft
Performing full fine-tuning (FFT) in Unsloth with 100% exact weight updates and optimized gradient checkpointing. Triggers include fft, full fine-tuning, full_finetuning, exact fine-tuning, and weight updates.
unsloth-gguf
Exporting fine-tuned models to GGUF format for deployment in llama.cpp, Ollama, and local serving tools. Triggers: gguf, quantization export, llama.cpp, ollama, save_pretrained_gguf, modelfile.
unsloth-grpo
Implementation of Group Relative Policy Optimization (GRPO) for training reasoning models, optimized for 8x memory savings (triggers: GRPO, reasoning, DeepSeek-R1, reinforcement learning, RLVR, GRPOTrainer, thinking tokens).
unsloth-inference
Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.
unsloth-long-context
Training models on extended context lengths using optimized RoPE scaling and memory-efficient attention kernels. Triggers: long context, max_seq_length, rope scaling, large context window, flex attention.
unsloth-lora
Configuring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tuning using triggers like lora, qlora, rslora, rank selection, lora_alpha, lora_dropout, and target_modules.
unsloth-models
Guidance on selecting and configuring supported model architectures like Llama 4, DeepSeek-R1, and Qwen3. Triggers: llama 4, deepseek-r1, qwen3, gemma 3, model selection, instruct vs base.
unsloth-orpo
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
unsloth-qlora
Advanced 4-bit quantization techniques using Unsloth and BitsAndBytes for extreme VRAM efficiency (triggers: QLoRA, 4-bit, load_in_4bit, bnb-4bit, VRAM optimization, dynamic quantization).
pytorch-core
Core PyTorch fundamentals including tensor operations, autograd, nn.Module architecture, and training loop orchestration. Covers optimizations like pin_memory and lazy module initialization. (pytorch, tensor, autograd, nn.Module, optimizer, training loop, state_dict, pin_memory, lazylinear, requires_grad)
prompt-engineering
Comprehensive prompt engineering techniques for Claude models. Use this skill when crafting, optimizing, or debugging prompts for Claude API, Claude Code, or any Claude-powered application. Covers system prompts, role prompting, multishot examples, chain of thought, XML structuring, long context handling, extended thinking, prompt chaining, Claude 4.x-specific best practices, and agentic orchestration including subagents, agent loops, skills, MCP integration, and multi-agent workflows.
uv-advanced
Advanced usage of uv, the extremely fast Python package and project manager from Astral. Use this skill when working with uv for project management (uv init, uv add, uv run, uv lock, uv sync), workspaces and monorepos, dependency resolution strategies (universal, platform-specific, constraints, overrides), Docker containerization, PEP 723 inline script metadata, uvx tool execution, Python version management, pip interface migration, pyproject.toml configuration, or any advanced uv workflow. Covers workspaces, resolution strategies, Docker best practices, CI/CD integration, and migration from pip/poetry/pipenv.
agentic-patterns
Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic, multi-agent, orchestration, ReAct, evaluator-optimizer, tool-use, handoff.
torchaudio
Audio signal processing library for PyTorch. Covers feature extraction (spectrograms, mel-scale), waveform manipulation, and GPU-accelerated data augmentation techniques. (torchaudio, melscale, spectrogram, pitchshift, specaugment, waveform, resample)
torch-compile
Optimize PyTorch with torch.compile (TorchDynamo/Inductor), focusing on compile overhead, graph breaks, and benchmark methodology. Use when speeding up PyTorch models or debugging compile behavior; triggers: torch.compile, torchdynamo, inductor, graph break, pytorch optimization.
tool-calling
Define and run tool-calling patterns for LLMs (schema design, call loops, validation, parallel calls). Use when building function/tool calling workflows or debugging tool selection and arguments; triggers: tool-calling, function-calling, tool schema, tool declaration, parallel function calling.
structured-outputs
Techniques for ensuring LLM responses adhere to strict JSON schemas, utilizing Pydantic models, JSON mode, and schema-based refusals. Triggers: structured-output, pydantic, json-schema, json-mode, llm-response-parsing.
pytorch-quantization
Techniques for model size reduction and inference acceleration using INT8 quantization, including Post-Training Quantization (PTQ) and Quantization Aware Training (QAT). (quantization, int8, qat, fbgemm, qnnpack, ptq, dequantize)
pytorch-onnx
Exporting PyTorch models to ONNX format for cross-platform deployment. Includes handling dynamic axes, graph optimization in ONNX Runtime, and INT8 model quantization. (onnx, onnxruntime, torch.onnx.export, dynamic_axes, constant-folding, edge-deployment)
pytorch-lightning
High-level training framework for PyTorch that abstracts boilerplate while maintaining flexibility. Includes the Trainer, LightningModule, and support for multi-GPU scaling and reproducibility. (lightning, pytorch-lightning, lightningmodule, trainer, callback, ddp, fast_dev_run, seed_everything)
pytorch-geometric
Library for Graph Neural Networks (GNNs). Covers MessagePassing layers, modular aggregation schemes, and handling large graphs via mini-batching with disjoint graph representation. (pyg, messagepassing, gnn, gcn, gat, edge_index, knn_graph, global_mean_pool)
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, distributeddataparallel, torchrun, nccl, rank, process-group)
pytorch-cuda
PyTorch CUDA environment and performance guidance, with emphasis on CUDA 13 toolkit/driver requirements, PyTorch wheel compatibility, and runtime checks. Use when configuring PyTorch on NVIDIA GPUs, debugging CUDA setup, or migrating to CUDA 13; triggers: pytorch cuda, cuda 13, driver version, nvcc, torch.version.cuda, tf32, streams.
ollama-rag
Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.
python-async
Asyncio patterns in Python for high-concurrency IO-bound tasks. Includes coroutines, task management, and asynchronous resource handling. Triggers: asyncio, python-async, coroutine, await, async-gather, async-generator, event-loop.
pytest-patterns
Advanced Python testing strategies with Pytest, covering fixtures, matrix testing with parametrization, and async test architecture. Triggers: pytest, fixtures, parametrize, pytest-asyncio, matrix-testing, yield-fixture.
numpy-ufuncs
Universal functions (ufuncs) for vectorization, including reductions, in-place operations, and custom Python-function wrapping. Triggers: ufunc, vectorize, reduce, accumulate, frompyfunc, in-place.
numpy-structured
Structured and record arrays for C-interoperability, binary blob interpretation, and multi-field tabular data handling. Triggers: structured array, record array, compound dtype, multi-field index.
numpy-string-ops
Vectorized string manipulation using the char module and modern string alternatives, including cleaning and search operations. Triggers: string operations, numpy.char, text cleaning, substring search.
Page 1347 of 1405 · 70201 results
