170 skills · sorted by relevance
Build Next.js applications with App Router patterns for page structure, data fetching, caching, and progressive page loading. Covers server and browser component responsibilities, route design, Server Actions, and migration from Pages Router.
Get guidance on distributed training with PyTorch FSDP, which splits model parameters across devices. The skill covers implementation, mixed precision, moving data to CPU memory, communication setup, and debugging distributed training code.
Split independent research or data-entry tasks among parallel workers. Provides a workflow for tracking completion in a table, testing one task first, and using a Python playbook to retry unfinished work and resume interrupted runs.
Convert .NET tests from xUnit.net v2 or v3 to MSTest v4 while keeping the existing test runner and target framework. Preserve assertions, shared setup, and parallel execution, then compare test counts and outcomes.
Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.
The English summary is being prepared. Showing the original description.
Speed up local parfor, parfeval, or spmd by switching to a thread-based parallel pool. Trigger when a user describes slow or disappointing local parallel performance, even if they don't mention threads. Symptoms: parfor on a laptop/workstation is slower than expected or "only slightly faster than for"; parfor scales poorly with the number of workers; ticBytes/tocBytes, the Parallel Pool dashboard, mpiprofile, or system tools show large per-worker data transfer; large broadcast variables or sliced inputs make iterations slow; opening a process pool dominates a short workload; user mentions serialisation or data transfer overhead. Also trigger on any question about whether code or a function works on a thread pool. For non-pool MATLAB performance work (vectorisation, preallocation, profiling), defer to matlab-optimize-performance.
The English summary is being prepared. Showing the original description.
Use when a database schema or data-meaning change needs Parallel Change, including expand, migrate, and contract sequencing for column renames, type or data reinterpretation, large-table backfills, relationship-table changes, enum/status transitions, timezone/default changes, and index or uniqueness changes. This should trigger before framework-specific Flyway implementation guidance when deciding whether a migration needs a compatibility window or whether a simpler migration is sufficient. Part of Plinth Toolkit
The English summary is being prepared. Showing the original description.
Provides Next.js App Router data fetching patterns including SWR and React Query integration, parallel data fetching, Incremental Static Regeneration (ISR), revalidation strategies, and error boundaries. Use when implementing data fetching in Next.js applications, choosing between server and client fetching, setting up caching strategies, or handling loading and error states.
The English summary is being prepared. Showing the original description.
Full SEO audit powered by the DataForSEO API. Orchestrates 5 specialist subagents (keywords, technical, competitors, content, backlinks) hitting DataForSEO Keywords Data, SERP, On-Page, Backlinks, and Labs endpoints in parallel, then produces a composite SEO Score (0-100) with prioritized action plan and audit JSON ready for PDF export.
The English summary is being prepared. Showing the original description.
Next.js project structure, App Router conventions, file-based routing primitives, layouts, error boundaries, metadata, image and font optimization, configuration. Apply when implementing or modifying Next.js features. Use this skill to: - Pick the correct file convention (page/layout/loading/error/not-found/route/template/default). - Structure a feature within the App Router tree. - Set up metadata for SEO and OpenGraph. - Configure next.config.js for headers, redirects, image domains. - Use built-in fonts and images correctly. Do NOT use this skill for: - Server vs Client component boundaries (see server-component-patterns). - Data fetching patterns (see nextjs-data-fetching). - Complex routing (parallel/intercepting routes — see nextjs-routing). - Testing (see nextjs-testing).
The English summary is being prepared. Showing the original description.
Specific optimization strategies for Python scripts working with larger-than-memory datasets via Dask.
The English summary is being prepared. Showing the original description.
Implement asynchronous work and changing data streams in Android and Kotlin Multiplatform apps using Kotlin Coroutines and Flow. Apply patterns for parallel loading, UI state updates, cancellation, error handling, and tests that check emitted values.
Run machine learning training and predictions on cloud GPUs, then publish models as APIs that other applications can call. The skill guides Python-based setup, automatic scaling, persistent storage, parallel processing, and scheduled jobs.
Measure Python execution time and memory use to locate slow or resource-heavy code. Use profiling results to guide improvements in data structures, caching, input and output operations, algorithms, and parallel processing.
Design and improve Unity games that process large numbers of entities. Learn ECS, an approach that separates data from behavior, and apply Jobs and Burst patterns to organize parallel processing and address CPU performance bottlenecks.
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.
Run batch processing, scientific simulations, and machine learning training on Google Kubernetes Engine. Configure parallel jobs, queues that manage resource access, and distributed computation, with guidance on scaling idle capacity down and recovering from interruptions.
Guides LLM fine-tuning with Axolotl, from YAML configuration and dataset formats to distributed training across GPUs. Covers LoRA and QLoRA, methods that train on preferences, multimodal support, and troubleshooting using documentation references and code examples.
Work across multiple n8n instances through one MCP connection, the link used by an agent to call tools. Specify each operation’s target, verify where credentials will be stored, and recover when requests reach the wrong environment.
Convert NUnit 3 or 4 tests to MSTest v4 while keeping the existing target framework and test runner. The workflow translates assertions, test data, setup, and concurrency settings, then compares test counts and results.
Correct and improve existing MSTest tests using APIs supported by the installed version. Refine assertions and failure messages, update data-driven tests, fix setup and cleanup, and address MSTest diagnostics while preserving the project's established conventions.
Use this skill whenever the user wants to conduct an event study, create event study plots, test for parallel trends, implement difference-in-differences designs, or work with any panel data estimation that involves pre/post treatment comparisons. Trigger on phrases like "event study", "parallel trends", "pre-trends", "dynamic treatment effects", "leads and lags", "TWFE", "two-way fixed effects", "staggered adoption", "staggered treatment", "difference-in-differences", "DiD", "Sun and Abraham", "Callaway and Sant'Anna", "de Chaisemartin", "Borusyak", "did_multiplegt", "fixest", "did2s", "bacon decomposition", or any reference to plotting coefficients around a treatment event. Also trigger when the user uploads panel data and wants to estimate treatment effects with variation in treatment timing. All code is in R.
The English summary is being prepared. Showing the original description.
Start (or restart) a local Temps control plane built from this checkout, and the web dev server (`bun dev`) in `<checkout>/web`. Invoke when the user says "start temps", "restart temps", "launch the server", "kill and restart temps", or asks to bring the local server up after backend changes. Ports, database and data dir are allocated PER CHECKOUT (a "slot") so several worktrees/branches run side by side without killing each other or corrupting each other's schema — the first checkout you start in claims slot 0 (the familiar `:8080` / `:3000`); every other worktree gets its own slot and its own `temps_s<N>` database. Uses the `fast` cargo profile (release semantics, no debug symbols, parallel codegen) for quick rebuilds. Pass `split` (e.g. "start temps split", "/start-temps split") to launch the two-process proxy/console topology for testing that feature.
The English summary is being prepared. Showing the original description.
Fast in-memory DataFrame with lazy evaluation, parallel execution, Arrow backend. Use for tabular data in RAM (1–100 GB) when pandas is too slow. Expression API: select, filter, group_by, joins, pivots, window. Lazy mode enables predicate/projection pushdown. Reads CSV, Parquet, JSON, Excel, DBs, cloud. Larger-than-RAM: Dask; GPU: cuDF.
The English summary is being prepared. Showing the original description.