Results for “large scale”

Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis. Use when fixed-size chunks either lose surrounding context or dilute relevance in long documents, manuals, filings, or codebases. Covers sentence-window and parent-child or auto-merging strategies, base chunk sizing, and evaluation. Do not use when a single chunk scale already meets retrieval and generation needs.

The English summary is being prepared. Showing the original description.

Guides the end-to-end GDPR Data Protection Impact Assessment process under Article 35, including mandatory trigger identification per Art. 35(3), DPIA content requirements per Art. 35(7), and EDPB WP248rev.01 methodology. Activate for systematic profiling, large-scale special category processing, or large-scale public monitoring. Keywords: DPIA, Article 35, impact assessment, WP248, data protection, risk assessment.

The English summary is being prepared. Showing the original description.

Upscale images and video 2x to 4K/8K on the user's GPU through Guaardvark (Real-ESRGAN, HAT-L, SwinIR, two-pass). Use when the user asks to enlarge, sharpen, restore, or upscale a picture, a batch of pictures, or a video.

The English summary is being prepared. Showing the original description.

Template-based page generation at scale for SEO. Data-driven content, internal linking architecture, and automated optimization for large-scale content operations. Use when the user asks about programmatic SEO, pSEO, scaled content, template pages, or automated page generation.

The English summary is being prepared. Showing the original description.

Use this skill whenever you need to reason like John D. Rockefeller, founder of Standard Oil and American oil industrialist. Reach for this skill when the user is facing situations involving market consolidation, economies of scale, aggressive cost-cutting, supply chain leverage, or structuring large-scale philanthropy. It is highly applicable for questions about eliminating operational waste, dealing with fierce competition, negotiating from a position of immense scale, or building self-sustaining charitable foundations. Trigger this skill for topics like monopolies, ruthless efficiency, corporate PR crises, and strategic acquisitions, even if the user doesn't explicitly name Rockefeller.

The English summary is being prepared. Showing the original description.

Observational cosmology from Hubble's law to the CMB. Covers redshift, Hubble expansion, the cosmological parameters, the cosmic microwave background, large-scale structure, galaxy rotation curves and dark matter, Type Ia SNe and dark energy, and the current state of Lambda-CDM. Use when reasoning about the large-scale universe, interpreting cosmological surveys, or teaching the Big Bang evidence chain.

The English summary is being prepared. Showing the original description.

Execute large-scale automated code transformations safely and idempotently. Use when renaming symbols across a codebase, migrating API call-sites, enforcing new patterns at scale, or applying structural edits to many files at once. Triggers on: 'codemod', 'mass rename', 'migrate all usages', 'transform codebase', 'apply pattern at scale', AST-based refactoring, or any task requiring consistent edits across 10 or more files.

The English summary is being prepared. Showing the original description.

Stores and operates on sparse expression matrices for single-cell and large bulk RNA-seq, covering dgCMatrix/dgRMatrix/dgTMatrix when-each-is-fast, the dgCMatrix (CSC, R) <-> CSR (Python) implicit transpose, AnnData (cells-rows) <-> SingleCellExperiment (cells-cols) orientation flip, HDF5/h5ad vs Zarr cloud-native shift, HDF5SummarizedExperiment + DelayedArray for out-of-memory bulk, scanpy backed mode for large h5ad, the ~10-15% density crossover where dense beats sparse, 10X format proliferation (MTX vs CellRanger H5 vs h5ad), the dense-conversion memory blow-up, and Dask + Zarr for consortium-scale matrices. Use when choosing sparse format, working with single-cell-sized matrices, importing/exporting 10X, debugging R/Python interop transposes, processing matrices too large for RAM, or building cloud-native pipelines.

The English summary is being prepared. Showing the original description.

Expert-level cosmology covering the Big Bang, cosmic expansion, dark matter, dark energy, CMB, large-scale structure, and observational cosmology.

The English summary is being prepared. Showing the original description.

Stores and operates on sparse expression matrices for single-cell and large bulk RNA-seq, covering dgCMatrix/dgRMatrix/dgTMatrix when-each-is-fast, the dgCMatrix (CSC, R) <-> CSR (Python) implicit transpose, AnnData (cells-rows) <-> SingleCellExperiment (cells-cols) orientation flip, HDF5/h5ad vs Zarr cloud-native shift, HDF5SummarizedExperiment + DelayedArray for out-of-memory bulk, scanpy backed mode for large h5ad, the ~10-15% density crossover where dense beats sparse, 10X format proliferation (MTX vs CellRanger H5 vs h5ad), the dense-conversion memory blow-up, and Dask + Zarr for consortium-scale matrices. Use when choosing sparse format, working with single-cell-sized matrices, importing/exporting 10X, debugging R/Python interop transposes, processing matrices too large for RAM, or building cloud-native pipelines.

The English summary is being prepared. Showing the original description.

Stores and operates on sparse expression matrices for single-cell and large bulk RNA-seq, covering dgCMatrix/dgRMatrix/dgTMatrix when-each-is-fast, the dgCMatrix (CSC, R) <-> CSR (Python) implicit transpose, AnnData (cells-rows) <-> SingleCellExperiment (cells-cols) orientation flip, HDF5/h5ad vs Zarr cloud-native shift, HDF5SummarizedExperiment + DelayedArray for out-of-memory bulk, scanpy backed mode for large h5ad, the ~10-15% density crossover where dense beats sparse, 10X format proliferation (MTX vs CellRanger H5 vs h5ad), the dense-conversion memory blow-up, and Dask + Zarr for consortium-scale matrices. Use when choosing sparse format, working with single-cell-sized matrices, importing/exporting 10X, debugging R/Python interop transposes, processing matrices too large for RAM, or building cloud-native pipelines.

The English summary is being prepared. Showing the original description.

Helps you build similarity search with FAISS to find nearby vectors, numerical representations of data. Covers index selection, saving and loading, GPU use, and tuning search speed, accuracy, and memory consumption for large datasets.

• Building similarity search over large vector datasets
• Choosing indexes for speed, accuracy, and memory use
• Running batch searches on GPUs

Create an HTML pitch deck for Series A fundraising, explaining growth, expansion, and the case for venture-scale returns. Large headlines and a red accent help organize the story around a few clear statements per slide.

• Preparing a Series A fundraising pitch
• Presenting growth and expansion to investors
• Turning a founder's vision into bold slides

Search document collections by meaning using embeddings, numerical representations of text. Compare text similarity, route queries among a few predefined patterns, and use a compressed search index when memory is limited.

• Finding documents with similar meaning
• Comparing the similarity of two pieces of text
• Reducing memory use for large vector collections

Organize single-cell measurements with cell and gene metadata, read and write h5ad or Zarr files, and prepare subsets or combined datasets. Includes guidance on handling large annotated matrices without loading all measurement values into memory.

• Read and write h5ad or Zarr datasets
• Combine experimental batches with source labels
• Select cells or genes using metadata

Implement large parallel workloads in Java with Azure Batch. Manage groups of computing machines, organize jobs and tasks, inspect progress and output, adjust computing capacity, and schedule recurring jobs using SDK examples.

• Running many computing tasks in parallel
• Adjusting machine counts to match pending work
• Checking task progress, exit codes, and output

Improve Bazel builds in large repositories containing multiple projects. Get guidance on build configuration, shared remote caches, remote execution, dependency management, custom build rules, and diagnosing build problems.

• Set up Bazel for a monorepo
• Configure remote caching and execution
• Review slow build configurations

Plan large sets of search-focused pages using templates and data, such as location guides, comparisons, and directories. Define unique content for each page, URL patterns, internal links, and quality checks before launch.

• Planning service pages for multiple locations
• Designing templates for product comparison pages
• Structuring a directory or industry glossary

Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.

• Preprocessing datasets larger than memory
• Running batch predictions across multiple GPUs
• Preparing image and tabular data for training

Plan large sets of search-focused pages using templates and data, such as location, comparison, and integration pages. Define unique content, URL patterns, internal links, launch checks, and monitoring metrics for a structured publishing plan.

• Planning service pages for multiple locations
• Designing product comparison or integration page templates
• Expanding a directory using available data

Plan and audit large sets of pages generated from structured data. Assess source quality, template uniqueness, URLs, and internal links, then identify thin content and unnecessary search indexing with prioritized recommendations and staged publishing guidance.

• Plan directory or glossary pages from structured data
• Audit repetitive content across generated pages
• Design URL patterns and automated internal links

Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.

• Preprocessing datasets larger than memory
• Running batch predictions across multiple GPUs
• Preparing image and tabular data for training

Implement and troubleshoot large-model training with DeepSpeed across multiple GPUs. The skill covers memory optimization, parallel training, and numerical precision choices, alongside examples for storage transfers and models that divide work among specialized components.

• Review settings for distributed model training
• Tune transfers between NVMe storage and tensors
• Configure training with specialized model components

Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state and `@Observable` data flow, view composition, resizable layouts, safe areas, display scale, performance, lists, environment, localization, animation, Liquid Glass, and API migration. Also use for iPhone Duo, foldable, or large-display layouts (`NavigationSplitView` on large displays, iPhone tab sidebar, two-column reflow, foldable grids, `ArrangementView`, `ReservedRegion`), hinge effects, vertical bars, `@State` initialization or synthesized-property diagnostics, `@ContentBuilder` ambiguity, `reorderable` drag/drop, custom `AsyncImage` `URLSession`, swipe actions outside List, item-bound `alert`/`confirmationDialog`, `ToolbarOverflowMenu`, `AnimatableValues`, Document APIs (`Document`/`DocumentReader`), and Instruments `.trace` capture or analysis.

The English summary is being prepared. Showing the original description.