moai-baas-convex-ext
Enterprise Convex Real-Time Backend with AI-powered reactive database architecture, Context7 integration, and intelligent synchronization orchestration for collaborative applications
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Enterprise Convex Real-Time Backend with AI-powered reactive database architecture, Context7 integration, and intelligent synchronization orchestration for collaborative applications
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
Trace agent decision-making, tool selection, and reasoning chains
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search in FastAPI backends. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Use for implementing meal planner, pantry, shopping lists, recipes, profile, or scanner flows and their service contracts.
Search past AI sessions with CASS. Use when looking for past solutions, searching session history, finding how something was done before, or when the user mentions "cass", "history", or "past sessions".
Build real-time voice and video applications with Google's Gemini Live API. Use when implementing bidirectional audio/video streaming, voice assistants, conversational AI with interruption handling, or any application requiring low-latency multimodal interaction with Gemini models. Covers WebSocket streaming, voice activity detection (VAD), function calling during conversations, session management/resumption, and ephemeral tokens for secure client-side connections.
Delegate asynchronous coding tasks to Jules (Google's AI coding agent) to maximize efficiency. Use for code reviews, refactoring, adding tests, bug fixes, and documentation. Proactively suggest Jules delegation when appropriate. Invoke when user asks to interact with Jules, create sessions, check task status, or when tasks are suitable for async delegation.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
A meta-skill for authoring high-performance, verifiable, long-running MCP skills using Code Mode. This skill blends Anthropic and OpenAI skill-authoring guidance with Code-Mode-first, MCP-backed execution, dynamic context discovery, and file-backed agent harnesses.
Interactive planning and execution for complex tasks. Use when breaking down multi-step projects (planning) or executing approved plans through delegation (execution). Planning creates milestones with specifications; execution delegates to specialized agents.
Amazon Bedrock AgentCore platform for building, deploying, and operating production AI agents. Covers Runtime, Gateway, Browser, Code Interpreter, and Identity services. Use when building Bedrock agents, deploying AI agents to production, or integrating with AgentCore services.
Create and configure VoltAgent AI agents with tools, memory, hooks, and sub-agents. Use when building AI agents, adding agent tools, configuring VoltAgent memory, creating multi-agent workflows, or debugging VoltAgent integrations.
Build Slack as a communication channel for AI agents. Use when implementing Slack OAuth, webhooks, event processing, or creating agent-to-Slack messaging pipelines.
Overview of Clojure + Google ADK + Vertex AI development environment. Comprehensive lab for building production AI agents using Clojure as primary language, integrating Google ADK via Java SDK and Python libraries via libpython-clj. Includes healthcare pipeline with validated ROI (-99.4% time, -92.4% cost). Use when starting new projects, understanding architecture, or needing general context about the stack.
Detects context drift, conversation unfocus, and suggests refocusing strategies. Trigger: When conversation exceeds 50 messages, when multiple topics are mixed, when repeated errors occur, when confusion patterns are detected.
Comprehensive research, analysis, and content extraction system. Multi-source parallel research using available researcher agents. Deep content analysis with extended thinking. Intelligent retrieval for difficult sites. Fabric pattern selection for 242+ specialized prompts. USE WHEN user says 'do research', 'extract wisdom', 'analyze content', 'find information about', or requests web/content research.
Install Claude skills from .skill files. Use when installing a new skill provided by the user as a .skill file (which is a zip archive containing the skill directory structure).
LLMアプリケーションの設計・運用・評価・最適化。プロンプト管理、RAG構築、ファインチューニング、評価パイプライン、コスト最適化、本番運用。「LLM」「プロンプト」「RAG」「ファインチューニング」「AI運用」「評価」に関する質問で使用。