1,243 件 ・ 関連度順
概要と使いどころ
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
日本語の概要は準備中です。原文の説明を表示しています。
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
日本語の概要は準備中です。原文の説明を表示しています。
Automated dimensional analysis — Buckingham Pi theorem, non-dimensionalization, unit validation with pint, and characteristic scale estimation. Use before any physics computation to verify consistency and reduce parameter space.
日本語の概要は準備中です。原文の説明を表示しています。
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
日本語の概要は準備中です。原文の説明を表示しています。
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
日本語の概要は準備中です。原文の説明を表示しています。
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.
日本語の概要は準備中です。原文の説明を表示しています。
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
日本語の概要は準備中です。原文の説明を表示しています。
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
日本語の概要は準備中です。原文の説明を表示しています。
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
日本語の概要は準備中です。原文の説明を表示しています。
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
日本語の概要は準備中です。原文の説明を表示しています。
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
日本語の概要は準備中です。原文の説明を表示しています。
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
日本語の概要は準備中です。原文の説明を表示しています。
End-to-end genome-scale metabolic modeling from genome sequence to flux predictions. Covers automated reconstruction with CarveMe, model validation with memote, FBA/FVA analysis, and gene essentiality prediction. Use when building metabolic models or predicting metabolic phenotypes from genomic data.
日本語の概要は準備中です。原文の説明を表示しています。
Authors portable, strongly-typed bioinformatics pipelines in the Common Workflow Language (CWL v1.2) as CommandLineTool/Workflow/ExpressionTool documents, validated with cwltool and run at scale on Toil/Arvados/Calrissian. Use when deciding CWL (portability/provenance/regulated) vs Nextflow/WDL/Snakemake; declaring secondaryFiles for indexed companions (.bai/.fai/.dict/.tbi and the caret rule); putting resources/containers under requirements (must-hold) vs hints (advisory) to avoid silent OOM; choosing scatterMethod (dotproduct vs flat_/nested_crossproduct); preferring $(...) parameter refs over ${...} JavaScript for portability; pinning DockerRequirement images; or emitting a CWLProv provenance object for audited/clinical settings.
日本語の概要は準備中です。原文の説明を表示しています。
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
日本語の概要は準備中です。原文の説明を表示しています。
Designs and analyzes stable-isotope-resolved metabolomics (SIRM / isotope tracing / fluxomics) experiments that measure metabolic ACTIVITY via 13C/15N/2H tracers, distinct from steady-state pool profiling. Covers tracer choice, isotopologue vs isotopomer, mass-isotopomer distributions (MID), fractional enrichment, the mandatory natural-abundance + tracer-purity correction (IsoCor, AccuCor), and the metabolic/isotopic steady-state vs non-stationary (INST-MFA) distinction. Use when feeding a labeled tracer and interpreting labeling patterns, correcting raw isotopologue intensities, computing or plotting an MID, or deciding tracing vs abundance profiling. For absolute pool concentration and MRM mechanics see metabolomics/targeted-analysis; for constraint-based genome-scale flux (FBA, not empirical tracing) see systems-biology/flux-balance-analysis; for feature detection see metabolomics/xcms-preprocessing; for pathway enrichment that ignores the pool-vs-flux caveat see metabolomics/pathway-mapping.
日本語の概要は準備中です。原文の説明を表示しています。
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
日本語の概要は準備中です。原文の説明を表示しています。
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup.
日本語の概要は準備中です。原文の説明を表示しています。
Build AI content generation systems at scale. TRIGGERS - Use when user needs help with ai-content-generation-system related tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Build AI batch processing systems for scale. TRIGGERS - Use when user needs help with ai-batch-processor related tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Transform images with resize, crop, smart crop, upscale, remove background, and 20+ operations.
日本語の概要は準備中です。原文の説明を表示しています。
Imports FBX meshes into CARLA on UE 5.8 as spawnable props — drives the editor headlessly to import the mesh, derives the prop size from its measured bounds, and registers it in PropParameters.json so it appears in the blueprint library as static.prop.<name>. Handles the FBX unit-scale problem, verifies the result against a running server, and can revert cleanly. Use when the user asks to "import a prop", "add a custom mesh/object to CARLA", "make my model spawnable", or a prop imports but never shows up in the blueprint library.
日本語の概要は準備中です。原文の説明を表示しています。
Detects focal chromatin loops (point interactions / corner-dots) in balanced Hi-C and Micro-C contact maps and aggregates/validates a loop set. Covers de-novo calling with cooltools dots (HiCCUPS-style 4-background local enrichment with lambda-chunked FDR), chromosight (template-correlation), and Mustache (scale-space blob detection); aggregate peak analysis (APA) via cooltools pileup for confirmation; the depth/resolution prerequisite (de-novo needs ~5-10kb resolution = hundreds of millions to billions of valid pairs); consensus across callers and convergent-CTCF support as validation; and differential loops via union anchors plus chromosight quantify. Use when calling chromatin loops or dots from a cooler, deciding whether a map is deep enough to call de-novo vs running APA on known CTCF/cohesin anchors, building an aggregate peak pileup, comparing loops across conditions, or validating loop calls. For HiChIP/PLAC-seq/PCHi-C protein-anchored data use FitHiChIP/MAPS, not dots.
日本語の概要は準備中です。原文の説明を表示しています。