majiayu000/claude-skill-registry - 第 39 页

numpy

N-dimensional array computing library providing array types, vectorized operations, linear algebra, FFT, random sampling, and testing utilities.

原文语言：英语

transformers

python library

原文语言：英语

torch

PyTorch provides tensors with automatic differentiation plus neural network utilities for building and training models.

原文语言：英语

soliton-detection

Topological soliton detection and agency bridge with anyonic fusion algebra for concept composition

原文语言：英语

synapse-specialized-actions

Explains specialized Synapse action classes for specific workflows. Use when the user mentions "BaseTrainAction", "BaseExportAction", "BaseUploadAction", "BaseInferenceAction", "BaseDeploymentAction", "AddTaskDataAction", "train action", "export action",…

原文语言：英语

speech-pathology-ai

Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice disorders, fluency intervention, and assistive communication technology. Activate on 'speech therapy', 'articulation', 'phoneme…

原文语言：英语

speech-pathology-ai

Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice disorders, fluency intervention, and assistive communication technology. Activate on 'speech therapy', 'articulation', 'phoneme…

原文语言：英语

splitting-datasets

Split datasets into training, validation, and test partitions with the right stratification and temporal rules. Use as a narrow preprocessing helper once the broader ML workflow is already chosen, not as the main route owner for an end-to-end ML task.

原文语言：英语

stellogen

Stellogen Skill

原文语言：英语

synthetic-data-generation

LLM-generated training data, augmentation strategies, distillation datasets, self-instruct and Evol-Instruct patterns, quality filtering pipelines.

原文语言：英语

bio-small-rna-seq-target-prediction

Predict miRNA target genes using sequence-based algorithms and database lookups. Use when identifying potential mRNA targets of differentially expressed or functionally important miRNAs.

原文语言：英语

hotdog

Hot dog or not? Classify food photos and battle Nemotron. Use when a user sends a food photo, asks if something is a hot dog, or says 'hotdog', '/hotdog', or 'hot dog battle'.

原文语言：英语

time-series-forecaster

Time series forecasting with ARIMA, Prophet, LSTM, and statistical methods. Activates for "time series", "forecasting", "predict future", "trend analysis", "seasonality", "ARIMA", "Prophet", "sales forecast", "demand prediction", "stock prediction". Handles…

原文语言：英语

time-series-ml

Build time series forecasting and anomaly detection with transformers and classical methods

原文语言：英语

tokenizer-design

BPE, WordPiece, SentencePiece, and Unigram tokenizer training, vocabulary optimization, domain extension, and multilingual design.

原文语言：英语

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,…

原文语言：英语

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)

原文语言：英语

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)

原文语言：英语

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)

原文语言：英语

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…

原文语言：英语

tracing

Imported skill tracing from langchain

原文语言：英语

train-model

Execute model training with optimization algorithms. Use when running training loops on datasets.

原文语言：英语

transformers

Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API, fine-tuning models with Trainer, or handling text, vision, audio, and multimodal tasks.

原文语言：英语

tripartite-decompositions

GF(3)-balanced structured decompositions for parallel computation. Decomposes problems into MINUS/ERGODIC/PLUS components with sheaf-theoretic gluing. Use for FPT algorithms, skill allocation, or any 3-way parallel workload.

原文语言：英语

two-sigma-ml-at-scale

Build trading systems in the style of Two Sigma, the systematic investment manager pioneering machine learning at scale. Emphasizes alternative data, distributed computing, feature engineering, and rigorous ML infrastructure. Use when building ML pipelines…

原文语言：英语

ui-detector

YOLO UI元素检测器项目管理。训练自定义模型识别界面元素（按钮、输入框、二维码等），用于半自动化操作。

ultrametric-distance

Non-Archimedean distance metrics for hierarchical clustering and p-adic analysis

原文语言：英语

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…

原文语言：英语

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).

原文语言：英语

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).

原文语言：英语

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.

原文语言：英语

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.

原文语言：英语

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.

原文语言：英语

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).

原文语言：英语

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.

原文语言：英语

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.

原文语言：英语

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.

原文语言：英语

unsloth-orpo

One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).

原文语言：英语

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).

原文语言：英语

unsloth-training

Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export. Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker…

原文语言：英语