majiayu000/claude-skill-registry - 第 36 页

numpy-indexing

Advanced indexing techniques including slicing, fancy indexing, and boolean masks, along with memory implications of views vs. copies. Triggers: indexing, slicing, fancy indexing, boolean mask, np.where, np.ix_.

原文语言：英语

numpy-interop

Protocols for cross-library data exchange including DLPack, buffer interfaces, and __array_ufunc__ for overriding NumPy functions. Triggers: DLPack, interoperability, __array_interface__, __array_ufunc__, buffer protocol.

原文语言：英语

numpy-masked

Masked arrays for robust handling of missing or invalid data, ensuring they are excluded from statistical and mathematical computations. Triggers: masked array, numpy.ma, missing data, invalid values, hard mask.

原文语言：英语

numpy-memory

Deep dive into memory layout, including strides, C vs Fortran order, and zero-copy view generation via stride tricks. Triggers: strides, C-order, Fortran-order, memory locality, stride_tricks.

原文语言：英语

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.

原文语言：英语

nvidia-nemo

NVIDIA NeMo framework for building and training conversational AI models. Use for NeMo Retriever models, RAG (Retrieval-Augmented Generation), embedding models, enterprise search, and multilingual retrieval systems.

原文语言：英语

oapply-colimit

oapply operad algebra evaluation via colimits with Specter-style composition patterns

原文语言：英语

occlusion-trace-meta-proof

Generate meta-proofs for occluded reasoning traces.

原文语言：英语

offline-vs-online-eval

* **Depends on**: None * **Compatible with**: None * **Conflicts with**: None * **Related Skills**: None # Overview Comprehensive guide to offline and online evaluation strategies for AI/ML models, in

原文语言：英语

omnihuman1-video

OmniHuman1によるAIアバター・リップシンク動画生成ガイド。 Use when: (1) user says「AIアバター」「リップシンク」「OmniHuman」, (2) user wants talking head videos from images, (3) user mentions「アバター動画」「1枚の画像から動画」. Do NOT use for: 実写動画編集（video-agentを使用）、 アニメ制作（anime-productionを使用）。

原文语言：日语

openai-whisper

Local speech-to-text with the Whisper CLI (no API key).

原文语言：英语

openai-whisper

Conversão local de voz para texto com o Whisper CLI (sem necessidade de chave de API).

原文语言：英语

openai-whisper

Local speech-to-text with the Whisper CLI (no API key).

原文语言：英语

operad-compose

Operad Composition Skill (PLUS +1)

原文语言：英语

output-waehlen

Output wählen im KI-Governance: Diese Output-Weiche für Ki Governance entscheidet, ob Memo, Antrag, Schriftsatz, Tabelle, Risikoampel, Fragenliste oder Mandantenbrief der richtige nächste Schritt ist.

原文语言：德语

own

Use when the user asks for a debrief on recent work, wants to check what they actually own versus what AI carried, or asks to be quizzed on their codebase. Triggers on "debrief", "what do I own", "own this", "quiz me on the code". User-invoked only — never…

原文语言：英语

pathology-roi-selector

Select and extract regions of interest (ROI) from whole slide images (WSI) for AI training data preparation and pathology research.

原文语言：英语

bio-metabolomics-pathway-mapping

Map metabolites to biological pathways using KEGG, Reactome, and MetaboAnalyst. Perform pathway enrichment and topology analysis. Use when interpreting metabolomics results in the context of biochemical pathways.

原文语言：英语

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms…

原文语言：英语

phase-space-transformation

Coordinate changes preserving dynamics

原文语言：英语

photo-content-recognition-curation-expert

Expert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition, perceptual hashing for de-duplication, screenshot/meme detection, burst photo selection, and quick indexing strategies. Activate on…

原文语言：英语

plasma-mind

Plasmoid consciousness detector. Maps Monad-Stokes fluid dynamics to ANY flow system, identifies Birkeland-like current structures, computes plasmoid consciousness thresholds (Psi > phi^{-5}), and extracts Nambu Hamiltonians {H1,H2,H3}=1. The cosmic nervous…

原文语言：英语

bio-population-genetics-population-structure

Analyze population structure using PCA and admixture analysis with PLINK and ADMIXTURE. Identify population clusters, assess ancestry proportions, visualize genetic structure, and choose optimal K for admixture models. Use when analyzing population…

原文语言：英语

powergraph-gnn-research

Research pipeline for topology-aware GNN representation learning on power grids using the PowerGraph benchmark. Use when (1) building physics-guided GNNs for power flow (PF), optimal power flow (OPF), or cascading failure prediction, (2) implementing…

原文语言：英语

predictive-analytics

ML-based estimation patterns, confidence intervals, and predictive modeling. Reference this skill when forecasting costs or time.

原文语言：英语

prepare-dataset

Process and validate datasets for training. Use when setting up data pipelines.

原文语言：英语

progress-photo-analyzer

Analyze construction site photos to track progress, detect safety issues, and compare against BIM models using computer vision.

原文语言：英语

propagators

Sussman/Radul propagator networks for constraint propagation and bidirectional

原文语言：英语

protein-phylogeny

Protein (gene) phylogeny inference pipeline: generates a .qmd analysis script that performs alignment, optional trimming, and tree building. Use when building phylogenetic trees from protein sequences, aligning protein families, running IQ-TREE or MAFFT for…

原文语言：英语

prove

Formal theorem proving with research, testing, and verification phases

原文语言：英语

pymc-modeling

Bayesian statistical modeling with PyMC v5+. Use when building probabilistic models, specifying priors, running MCMC inference, diagnosing convergence, or comparing models. Covers PyMC, ArviZ, pymc-bart, pymc-extras, nutpie, and JAX/NumPyro backends. Triggers…

原文语言：英语

pyopenms

Complete mass spectrometry analysis platform. Use for proteomics workflows feature detection, peptide identification, protein quantification, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. Best for proteomics, comprehensive MS…

原文语言：英语

python-scientific-computing

Python for engineering analysis, numerical computing, and scientific workflows using NumPy, SciPy, SymPy

原文语言：英语

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,…

原文语言：英语

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:…

原文语言：英语

pytorch-deployment

Comprehensive guide for deploying PyTorch models to production, covering export formats, optimization techniques, and deployment patterns.

原文语言：英语

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,…

原文语言：英语

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)

原文语言：英语

pytorch-ml-training

PyTorch training opinions, pitfalls, and non-obvious patterns. Covers distributed training (DDP/FSDP), optimizer configuration, gradient accumulation, schedulers, and flash attention. Use when scaling training, debugging distributed setups, or making…

原文语言：英语

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)

原文语言：英语