Loading...
Loading...
Found 208 Skills
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
Next.js adapter for embedding emulators directly in a Next.js app via @emulators/adapter-next. Use when the user needs to embed emulators in Next.js, set up same-origin OAuth for Vercel preview deployments, create an emulate catch-all route handler, configure Auth.js/NextAuth with embedded emulators, add persistence to embedded emulators, or wrap next.config with withEmulate. Triggers include "Next.js emulator", "adapter-next", "embedded emulator", "same-origin OAuth", "Vercel preview", "createEmulateHandler", "withEmulate", or any task requiring emulators inside a Next.js app.
Guide RCCA/8D problem definition using 5W2H and IS/IS NOT analysis. Transforms scattered failure data into precise, measurable problem statements that bound investigation scope without embedding cause or solution. Use when defining problems for root cause analysis, writing D2 sections of 8D reports, analyzing nonconformances, investigating failures, or when user mentions problem definition, problem statement, RCCA, 8D, failure analysis, or corrective action.
Native SwiftUI WebKit integration with the new WebView struct and WebPage observable class. Covers WebView creation from URLs, WebPage for navigation control and state management, JavaScript execution (callJavaScript with arguments and content worlds), custom URL scheme handlers, navigation management (load, reload, back/forward), navigation decisions, text search (findNavigator), content capture (snapshots, PDF generation, web archives), and configuration (data stores, user agents, JS permissions). Use when embedding web content in SwiftUI apps instead of the old WKWebView + UIViewRepresentable/NSViewRepresentable bridge pattern. This is a brand new API — do NOT use the old WKWebView wrapping approach.
Skill for operating PocketBase backend via REST API and Go package mode. Provides collection CRUD, record CRUD, superuser/user authentication, backup & restore, migration file generation (JS and Go), Go hooks, custom routes, and design guidance for API rules, relations, and security patterns. Use for requests related to PocketBase, pb_migrations, collection management, record operations, Go framework embedding, and backend design.
Generate text embeddings and rerank documents via Together AI. Embedding models include BGE, GTE, E5, UAE families. Reranking via MixedBread reranker. Use when users need text embeddings, vector search, semantic similarity, document reranking, RAG pipeline components, or retrieval-augmented generation.
Generate a standards-aligned browser favicon.ico from a user-supplied source image, embedding PNG rasters at 32×32, 48×48, and 180×180 in one ICO container. Use when the user asks to create a favicon, 生成 favicon、网站图标、从图片做 ico、favicon.ico、create favicon from image. 从用户提供的源图生成含 32/48/180 三档尺寸的 favicon.ico（ICO 内嵌 PNG）。若用户未上传或未指定可用源图，必须中止并提示上传/路径。
Knowledge Base RAG implements the complete Retrieval-Augmented Generation pipeline: document ingestion, intelligent chunking, embedding generation, vector store indexing, semantic retrieval, and grounded response generation.
Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate
Cluster vectors by similarity using npx ruvector k-means or density-based methods with labeled group summaries
AI/ML APIs, LLM integration, and intelligent application patterns
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.