email-assistant
Autonomous email agent that reads, summarizes, triages, and responds to emails via Gmail. Use when user wants help managing their inbox or processing emails.
Найдите подходящую возможность для вашего агента.
Autonomous email agent that reads, summarizes, triages, and responds to emails via Gmail. Use when user wants help managing their inbox or processing emails.
Build AI agents with OpenAI Agents SDK + Model Context Protocol (MCP) for tool orchestration. Supports multi-provider backends (OpenAI, Gemini, Groq, OpenRouter) with MCPServerStdio. Use this skill for conversational AI features with external tool access via MCP protocol.
Generate inline chat cards using DaisyUI components for user interactions. Use when creating interactive UI elements within a chat interface that require user input, confirmation, or selection. Supports affirmative/negative responses, multiple choice (radio), multiple select (checkbox), and content preview with feedback patterns.
Conducts rigorous academic research and document analysis using Gemini's advanced control features (Logprobs, Citations, Long Context).
Creates a battle-tested ChatGPT-style chatbot widget that solves real-world production issues. Features infinite re-render protection, text selection "Ask AI", RAG backend integration, streaming SSE, and comprehensive performance monitoring.
Build embeddable chatbot widgets for web applications. Use when creating chat UIs, iframe embeds, or widget-based AI interfaces.
This skill should be used when the user asks to "build an AI agent", "create a chatbot", "use Cloudflare Agents SDK", "stateful AI agent", "WebSocket agent", or is developing AI agents on Cloudflare infrastructure.
Start a new learning session on a topic. Use when user wants to learn something new, begin studying, get taught a topic, or start a teaching conversation. Triggers on "teach me", "let's learn", "start session", "study [topic]", "explain [topic]".
Set up the embedding model for semantic search. model2vec-rs downloads models automatically; use when build fails or model download issues occur.
MANDATORY for ALL AI prompts - Automatically validate and improve AI system prompts,
Build AI agents using Google's Agent Development Kit (ADK) for Python. Use this skill when the user wants to create ADK agents, multi-agent systems, agents with tools, workflow agents (Sequential, Parallel, Loop), or deploy agents to Google Cloud. Triggers include mentions of "ADK", "Agent Development Kit", "google-adk", "adk agent", "multi-agent system", or requests to build AI agents with Google's framework.
Design and build Glif AI workflows. Use when creating new glifs, planning workflow structure, or understanding block types.
Systematic research workflow orchestrating multi-source research operations for comprehensive domain investigation. Sequential workflow from web search through GitHub exploration and documentation analysis to research synthesis. Use when researching new domains, gathering patterns, investigating technologies, or conducting comprehensive multi-source research for skill development.
Discover available effects, actions, and placeholders in a Sandestin project. Use when asking what effects exist, searching for functionality, or needing example invocations. Keywords: effects, actions, dispatch, describe, grep, sample.
Create, optimize, and debug high-performing prompts for Claude 4 models and GLM 4.7 (Z.ai) with production-ready templates and evidence-based techniques. Use this skill when the user asks to create a prompt, write a prompt, improve a prompt, build a prompt chain, design a system prompt, adapt a prompt for GLM 4.7, or needs prompt engineering guidance. Also handles prompt refinement and follow-up modifications.
Discover available effects, actions, and placeholders in a Sandestin project. Use when asking what effects exist, searching for functionality, or needing example invocations. Keywords: effects, actions, dispatch, describe, grep, sample.
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
Build accurate mental models of AI behavior: understand context windows, probabilistic generation, hallucination causes, and predict failure modes before they occur.
This skill should be used when the user asks to "orchestrate agents", "run /orchestrate", "manage parallel agents", "coordinate multiple agents", "decompose this task", or needs patterns for multi-agent workflows with parallel execution and task decomposition.
Create well-structured subagents for Claude Code with specialized expertise, proper tool configurations, and effective system prompts. Use when building custom subagents for code review, debugging, testing, data analysis, codebase research, or domain-specific workflows.