productivity▌

Generate a concise, professional equity research earnings preview for a single company. The output is a self-contained HTML file targeting 4-5 printed pages. The report is dense with figures and data, with tight narrative that gets straight to the point.

Identify and extract reusable components, design tokens, and patterns into a cohesive design system. \n \n Analyzes target areas to find repeated UI patterns, hard-coded values, and inconsistent variations worth systematizing \n Guides extraction planning including component APIs, token hierarchies, naming conventions, and migration strategies \n Emphasizes incremental growth: extract only patterns used 3+ times or with clear reuse potential, avoiding over-generalization \n Includes accessibilit

Pluggable memory and file backends for Deep Agents with ephemeral, persistent, and hybrid routing options. \n \n Four backend types: StateBackend (thread-scoped, ephemeral), StoreBackend (cross-session persistent), FilesystemBackend (real disk access for local dev), and CompositeBackend (route different paths to different backends) \n FilesystemMiddleware provides six file operation tools: ls , read_file , write_file , edit_file , glob , grep \n CompositeBackend uses longest-prefix matching to r

Rethink designs for different screens, devices, and contexts while maintaining consistency. \n \n Assess source and target contexts (device type, input method, screen size, connection speed, usage patterns) to identify what won't fit or work across platforms \n Apply context-specific strategies: single-column layouts and touch targets for mobile, two-column hybrid layouts for tablet, multi-column and hover states for desktop, narrow widths and inline CSS for email \n Use responsive techniques in

The recommended way to load textures in R3F.

Type-safe AI workflows with flows, agents, RAG, and multi-model support across TypeScript, Go, and Python. \n \n Supports Gemini, OpenAI, Anthropic, Ollama, and Vertex AI with pluggable model providers; deploy to Firebase Cloud Functions or Cloud Run \n Define type-safe flows with Zod schemas for inputs/outputs; includes streaming, tool calling, and agentic loops with auto-execution \n Built-in RAG with vector database integrations (Pinecone, pgvector, Firestore, Chroma, LanceDB) and retrieval-a

Implement horizontal data partitioning across multiple database servers. Covers sharding strategies, consistent hashing, shard key selection, and cross-shard querying patterns.

Professional image generation with advanced text rendering, photorealistic details, and semantic accuracy via Alibaba Qwen-Image-2.0-Pro. \n \n Excels at text-heavy designs including posters, banners, and multi-line text with fine-grained control over font, color, and positioning \n Generates 1–6 images per request with configurable dimensions (512–2048 pixels), negative prompts, and reproducible seeds \n Supports image editing and style transfer via reference images for outfit swaps and creativ

Guidance and reference material for instrumenting webapps with Azure Application Insights. \n \n Covers SDK setup, telemetry patterns, and configuration for ASP.NET Core and Node.js applications hosted in Azure \n Distinguishes between this skill (reference and guidance) and azure-prepare (actual implementation); invoke azure-prepare when the user wants to add instrumentation to their project \n Provides auto-instrumentation guidance for C# ASP.NET Core apps in Azure App Service, plus manual ins

Team leadership persona with standup coordination, meeting prep, task delegation, and team communication. \n \n Includes four core workflows: daily standup reports, 1:1 meeting preparation, weekly digests, and email-to-task delegation \n Integrates Google Workspace tools (Calendar, Gmail, Chat, Drive, Sheets) for unified team coordination and OKR tracking \n Supports calendar views, direct Chat messaging for report distribution, and data sanitization for sensitive information \n Requires five pr