2.7K skills · sorted by relevance
Performance optimization and measurement for .NET applications. Navigation skill covering Span, ArrayPool, memory management, benchmarking, profiling, Native AOT, and optimization patterns. For building high-performance applications. Keywords: performance, optimization, span, arraypool, benchmarking, profiling, memory, gc, aot, native-aot
The English summary is being prepared. Showing the original description.
MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times.
The English summary is being prepared. Showing the original description.
Investigate performance bottlenecks in REA analysis workflows and improve caching, queries, or shared processing. Compare completed tasks before and after changes while preserving correct results, examined coverage, and access to supporting evidence.
Build question answering and document retrieval workflows with DSPy by defining inputs, outputs, and reusable components. Use training examples and evaluation metrics to automatically optimize prompts and compare results before and after optimization.
Integrate Flash Attention into Transformer models to speed up attention, the calculation that relates input elements, while reducing GPU memory use. Covers PyTorch integration, performance measurement, output comparison, and a separate H100 optimization path.
Measure code performance and run benchmarks to investigate slow operations, regressions, or memory pressure. Establish a baseline, compare results under matching conditions, report variability, and rerun correctness tests after optimization.
Analyze performance in Claude Flow swarms, groups of agents working together. Identify delays in communication, processing, memory, and networking, then generate reports and prioritized recommendations. Compare previous runs or apply available automatic optimizations.
Write, review, and refactor React and Next.js code using performance guidelines from Vercel. Prioritized rules help identify sequential data requests, oversized JavaScript bundles, unnecessary re-renders, and other opportunities to improve loading and responsiveness.
Design popups, banners, and slide-in messages for email signups or purchases. Get copy, display timing, audience rules, frequency limits, mobile guidance, and test ideas, with attention to easy dismissal and accessible interaction.
Audit App Store or Google Play listings across six areas, including text, visuals, and reviews. Get a weighted score, specific copy and image recommendations, optional competitor comparisons, and prioritized changes tailored to the store and brand maturity.
Create and prepare marketing images for blogs, social posts, product showcases, and banners. Choose suitable generation or design tools, plan prompts and layouts, and optimize image dimensions, formats, and file sizes for web use.
Plan and review paid advertising across Google Ads, Meta, LinkedIn, and other platforms. Organize audiences, budgets, and bidding, then assess results using customer acquisition costs and sales data while separating evidence, hypotheses, and missing information.
Build and optimize quantum circuits with PennyLane, including models that combine quantum circuits with PyTorch or JAX. Explore molecular energy estimation and optimization problems, validate values and gradients in simulation, and prepare tested circuits for provider plugins.
Write, review, or refactor React and Next.js code using prioritized performance guidelines. Address sequential data requests, large bundles of browser code, server work, and unnecessary rendering, with explanations and code examples for each rule.
Analyze AWS spending by service, region, and resource tags to find unused resources and oversized configurations. Get specific cost reduction recommendations, estimated savings, and guidance for budgets and ongoing cost monitoring.
Build AWS applications that run without managing servers directly. Covers Lambda functions, APIs, DynamoDB storage, message-driven workflows with SQS/SNS, deployment through SAM/CDK, and reducing the delay when a function starts for the first time.
Coordinate specialist agents to investigate and improve application performance across databases, backend services, frontend code, and delivery infrastructure. Establish baseline measurements, address observed bottlenecks, validate changes with load tests, and set up monitoring to detect future slowdowns.
Improve mobile app listings on Apple App Store and Google Play Store through keyword research, competitor and review analysis, and listing revisions. Produce metadata suggestions, visual asset guidance, A/B test plans, and launch checklists.
Plan AI features for products, covering language model integration, RAG architecture that retrieves information for answers, prompt design, user experiences people can trust, and cost optimization. Use it to guide development decisions for production use.
Choose a model training method and configuration from paired response preferences or individual positive and negative ratings. Covers DPO, ORPO, KTO, and SimPO, including pair construction, repeated training rounds, and troubleshooting learning settings.
Investigate slow SQL using execution plans, which show how a database processes a query. Review indexes, filters, joins, and maintenance practices through PostgreSQL examples to identify bottlenecks and plan changes to queries or database structure.
Improve slow Apache Spark jobs by reviewing data partitions, caching, memory settings, and shuffles, which move data between workers. Use the guidance to investigate bottlenecks and tune pipelines for larger datasets.
Review DAX formulas, the expressions used for calculations in Power BI, and propose clearer, more maintainable alternatives. Identify repeated calculations, costly filtering, and error-handling issues, then explain changes and recommend ways to test them.
Improve LLM prompts using Arize production traces, evaluation results, and human feedback. Extract current instructions, identify recurring failures, revise the prompt, and compare experiments to measure changes in output quality and catch regressions.