Loading...
Loading...
Found 158 Skills
Vector search best practices for Azure DocumentDB using `cosmosSearch` — choosing between DiskANN / HNSW / IVF, creating indexes, tuning `lBuild` / `lSearch` / `maxDegree`, Product Quantization (up to 16,000 dims), half-precision (fp16) indexing, and normalizing embeddings for cosine similarity. Use when building RAG / semantic-search applications, creating a vector index, tuning recall/latency, or reducing vector-index memory footprint.
SwiftData patterns — autosave, relationships, dangerous predicates, CloudKit constraints, indexing, class inheritance. Use when writing, reviewing, or debugging SwiftData code.
Audits and improves SEO for Astro sites. Use when the user asks to audit, set up, or improve SEO on an Astro site, or mentions head metadata, structured data, JSON-LD, sitemaps, IndexNow, Open Graph images, schema endpoints, NLWeb, hreflang, or search engine indexing in an Astro project. Produces drop-in code routed through `@jdevalk/astro-seo-graph` and chains into `metadata-check` for generated SEO strings.
Provides comprehensive SAP Commerce Cloud (formerly Hybris) development guidance including type system modeling, service layer architecture, data management with ImpEx and FlexibleSearch, OCC API customization, B2C/B2B accelerator patterns, CronJobs, business processes, Solr search, promotions, caching, and Backoffice configuration. Use when the user asks to "create SAP Commerce extensions", "define item types in items.xml", "write ImpEx scripts", "implement service layer components (facades/services/DAOs)", "customize OCC REST APIs", "work with FlexibleSearch queries", "customize B2C or B2B accelerators", "configure Spring beans", "create CronJobs or scheduled tasks", "define business processes or order flows", "configure Solr search or indexing", "set up promotions or coupons", "configure caching", "customize Backoffice", mentions "Hybris development" or "SAP Commerce Cloud platform", or asks about troubleshooting SAP Commerce issues.
Extract TikZ diagrams from Beamer source, compile to PDF, convert to SVG with 0-based indexing. Use when updating TikZ diagrams for Quarto slides.
Use when you need to optimize database performance, schema design, indexing, and query performance across different database systems
Run and monitor existing (B2C/demandware/SFCC) jobs using the b2c cli, import/export site archives (IMPEX). Always reference when using the CLI to run jobs, import or export site archives, check job execution status, or trigger search indexing. For creating new jobs, use b2c-custom-job-steps skill instead.
Expert knowledge for Azure AI Video Indexer development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Video Indexer APIs/widgets, live camera indexing, custom speech/brand models, or Azure OpenAI integrations, and other Azure AI Video Indexer related development tasks. Not for Azure AI services (use microsoft-foundry-tools), Azure AI Vision (use azure-ai-vision).
Designs database schemas, indexing strategies, query optimization, and migration patterns for SQL and NoSQL databases. Use when designing tables, optimizing queries, fixing N+1 problems, planning migrations, or when asked about database performance, normalization, ORMs, or data modeling.
Use this when user provides a Yii2 codebase for analysis or migration planning. Provides 6-phase workflow: scan, capability extraction, dependency analysis, requirements extraction, semantic indexing, and migration roadmap. Apply when user mentions Yii2, PHP legacy modernization, or framework migration to NestJS
Query Google Search Console analytics, inspect URL indexing status, manage sitemaps, and run PageSpeed Insights audits. Use when the user needs SEO data, search performance reports, indexing diagnostics, or Core Web Vitals analysis.
Identify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies false vs true dependencies, provides sync-free alternatives. Triggers: sync-free, synchronization, .item(), .cpu(), host-device sync, eliminate syncs, CPU stall, non_blocking, set_sync_debug_mode, cudaStreamSynchronize, cudaEventSynchronize, remove syncs, async GPU.