188 skills · sorted by relevance
Diagnose failures in GKE HorizontalPodAutoscaler (HPA), which adjusts Pod counts automatically. Investigate missing metrics, unexpected scaling behavior, and slow reactions, then receive proposed configuration fixes or commands for review before deployment.
Conducts Privacy Impact Assessment for large-scale systematic monitoring under GDPR Article 35(3)(c). Covers CCTV and video surveillance, employee monitoring, location tracking, internet monitoring, and behavioural analytics. Applies EDPB WP248rev.01 criteria for systematic monitoring of publicly accessible areas. Keywords: DPIA, large-scale monitoring, CCTV, employee monitoring, systematic monitoring, surveillance, location tracking.
The English summary is being prepared. Showing the original description.
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
Use this skill when writing analytical SQL over time-series data with the TimescaleDB Toolkit (timescaledb_toolkit extension) hyperfunctions: approximate percentiles, statistical summaries, time-weighted averages, counter/gauge rates, uptime/heartbeat tracking, state durations, OHLC candlesticks, approximate distinct counts, top-N, and downsampling. **Trigger when user asks to:** - Compute percentiles/medians/p95/p99 over large or rolled-up time-series data - Compute rates or deltas from monotonic counters (Prometheus-style) or gauges - Compute time-weighted averages or integrals over irregularly sampled data - Track uptime/downtime from heartbeats, or time spent in each state - Build OHLC/candlestick or VWAP data for financial ticks - Store re-aggregatable summaries in continuous aggregates (two-step aggregation, rollup) - Approximate COUNT DISTINCT, find top-N / most frequent values, or downsample for charts **Keywords:** timescaledb_toolkit, hyperfunctions, percentile_agg, uddsketch, tdigest, approx_percentile, stats_agg, time_weight, counter_agg, gauge_agg, heartbeat_agg, state_agg, candlestick_agg, hyperloglog, approx_count_distinct, min_n, max_n, mcv_agg, lttb, asap_smooth, rollup, two-step aggregation
The English summary is being prepared. Showing the original description.
Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation. **Trigger when user asks to:** - Migrate or convert PostgreSQL tables to hypertables - Execute hypertable migration with minimal downtime - Plan blue-green migration for large tables - Validate hypertable migration success - Configure compression after migration **Prerequisites:** Tables already identified as candidates (use find-hypertable-candidates first if needed) **Keywords:** migrate to hypertable, convert table, Timescale, TimescaleDB, blue-green migration, in-place conversion, create_hypertable, migration validation, compression setup Step-by-step migration planning including: partition column selection, chunk interval calculation, PK/constraint handling, migration execution (in-place vs blue-green), and performance validation queries.
The English summary is being prepared. Showing the original description.
Programmatic SEO planning and audit: building or evaluating large sets of template-generated pages that target long-tail query patterns (e.g. "[service] in [city]", "[product] vs [product]", "[tool] for [use-case]"). Covers data-source and template design, thin/duplicate-content and doorway-page risks, per-page uniqueness and value thresholds, internal linking and hubs, indexation management (publish vs. noindex), and scaling without a manual action. Use whenever the user wants to generate many pages from a template/dataset, build location/comparison/use-case pages at scale, or asks why generated pages aren't indexing. Trigger on: "programmatic SEO", "pSEO", "generate pages at scale", "templated pages", "location pages at scale", "comparison pages", "[city] pages", "my generated pages aren't indexed", "doorway pages", "scale content". For one-off content use /content-writer; for keyword discovery use /keyword-research.
The English summary is being prepared. Showing the original description.
Expert knowledge for Azure Large Instances development including troubleshooting, limits & quotas, and integrations & coding patterns. Use when configuring Epic SKUs, sizing volume groups, tuning EHR storage, or resolving Epic–ALI connectivity/perf issues, and other Azure Large Instances related development tasks. Not for Azure Baremetal Infrastructure (use azure-baremetal-infrastructure), Azure Virtual Machines (use azure-virtual-machines), Azure Virtual Machine Scale Sets (use azure-vm-scalesets), Azure HPC Cache (use azure-hpc-cache).
The English summary is being prepared. Showing the original description.
Resizes, scales, and adjusts video resolution and dimensions using GPU-accelerated NVENC encoding via Volcengine LAS. Video resizing, video scaling, video upscaling, and video downscaling — change video resolution, enlarge or shrink video dimensions, and adjust video size for different platforms and screens. Video compression by reducing resolution and video transcoding and re-encoding with specific dimension constraints. Supports flexible min/max width and height ranges with aspect ratio preservation strategies (increase, decrease, or disable), including landscape to portrait conversion. Async submit-poll workflow with batch support. Use this skill when the user wants to resize or scale video resolution (upscale/downscale), change video dimensions for different platforms, compress videos by reducing resolution, transcode/re-encode videos with GPU NVENC, adjust aspect ratio including landscape-to-portrait conversion, adapt videos for mobile/web/social media, or batch process multiple videos.
The English summary is being prepared. Showing the original description.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
The English summary is being prepared. Showing the original description.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
The English summary is being prepared. Showing the original description.
Helps design ClickHouse tables, write analytical queries, and improve slow queries. Covers loading data in batches, preparing reusable summaries, and monitoring performance for large datasets, real-time dashboards, and time-series analysis.
Coordinate large migrations, refactors, and bulk renames by splitting them into independent tasks. After plan approval, 5–30 agents work in separate Git worktrees, isolated working directories, then review, test, and open a pull request for each task.
Plan large sets of search-focused pages using templates and data. The skill helps assess keyword demand, design useful page variations, organize internal links, choose a publishing platform, and check quality before launch.
Helps configure and troubleshoot DeepSpeed for training large models across multiple devices. Covers memory optimization, parallel training, and DeepNVMe storage transfers, with examples for tuning data movement and configuring models that divide work among specialized components.
Configure large language model training with NVIDIA Megatron-Core across multiple GPUs. This skill helps choose how to split computation, set training parameters, monitor GPU efficiency, and address memory limits or unstable training.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Build a workflow for importing large collections of audio, email, documents, or chats into knowledge pages. Test varied samples first, track progress in a persistent JSON file, and verify outputs before marking work complete.
Plan and troubleshoot large language and vision model training and inference. This guide uses hardware measurements to identify bottlenecks, address memory shortages and unstable training, and improve checkpointing, recovery, and performance across multiple GPUs and machines.
Configure large language model training across multiple NVIDIA GPUs with Megatron-Core. The skill helps choose how to split models and workloads, set training parameters, monitor performance, and address memory shortages or low GPU utilization.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation that requires planning before coding. Also triggers on Chinese keywords: "改造", "重写", "迁移", "重构", "大规模", "规范驱动". Performs full project analysis, task decomposition, documentation generation, project-level instruction and native memory surface resolution, progress tracking setup, and then executes the plan within the same session.
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.
Provides large-scale single-cell omics data manipulation using Genomic Data Structure (GDS) files. It combines dense and sparse matrices stored in GDS files and the Bioconductor infrastructure framework (SingleCellExperiment and DelayedArray) to provide out-of-memory data storage and large-scale manipulation using the R programming language.
The English summary is being prepared. Showing the original description.