majiayu000/claude-skill-registry - Page 39

numpy

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

Langue du texte source : anglais

transformers

python library

Langue du texte source : anglais

torch

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

Langue du texte source : anglais

soliton-detection

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

Langue du texte source : anglais

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",…

Langue du texte source : anglais

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…

Langue du texte source : anglais

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…

Langue du texte source : anglais

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.

Langue du texte source : anglais

stellogen

Stellogen Skill

Langue du texte source : anglais

synthetic-data-generation

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

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'.

Langue du texte source : anglais

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…

Langue du texte source : anglais

time-series-ml

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

Langue du texte source : anglais

tokenizer-design

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

Langue du texte source : anglais

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,…

Langue du texte source : anglais

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)

Langue du texte source : anglais

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)

Langue du texte source : anglais

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)

Langue du texte source : anglais

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…

Langue du texte source : anglais

tracing

Imported skill tracing from langchain

Langue du texte source : anglais

train-model

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

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…

Langue du texte source : anglais

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。

Langue du texte source : chinois

ultrametric-distance

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

Langue du texte source : anglais

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…

Langue du texte source : anglais

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).

Langue du texte source : anglais

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).

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

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).

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

unsloth-orpo

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

Langue du texte source : anglais

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).

Langue du texte source : anglais

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…

Langue du texte source : anglais