Найдите подходящую возможность для вашего агента.
MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.
Help with creating and managing Claude Code skills. Use when the user asks about creating skills, skill structure, or customizing Claude Code behavior.
Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.
Use when "tokenizers", "HuggingFace tokenizer", "BPE", "WordPiece", or asking about "train tokenizer", "custom vocabulary", "tokenization", "subword", "fast tokenizer", "encode text"
Use this skill when the conversation requires integrating AI services (such as image analysis, text generation, intelligent recognition, etc.) to generate integration code based on AI gateway or API
OpenCode.ai open-source AI coding agent comprehensive reference. Use when working with OpenCode TUI, CLI, IDE integration, configuring agents, tools, MCP servers, creating plugins, or developing with the SDK.
Single-file AI memory with memvid-cli for persistent knowledge storage and retrieval using text-embedding-3-large (3072 dimensions). Use when storing learnings, searching past context, managing session memory, or implementing long-term memory for AI agents. Triggers include "remember", "recall", "search memory", "store this", "what did we learn", or any task requiring persistent memory across sessions.
Manage persistent quantum memories across sessions. Use for storing, retrieving, organizing, and building upon past learnings and insights.
Expert prompt engineer that transforms vague user requests into optimized, detailed prompts for AI coding agents. Focus is on efficiency - helping users get complete results in one go without follow-up prompts. Triggers on prompt enhancement, prompt optimization, or when refining instructions for AI agents.
Build AI agents with Strands Agents SDK. Use when developing model-agnostic agents, implementing ReAct patterns, creating multi-agent systems, or building production agents on AWS. Triggers on Strands, Strands SDK, model-agnostic agent, ReAct agent.
Triggering and managing AI reflection cycles in StickerNest. Use when the user wants to run AI evaluation, trigger reflection, check AI quality, improve AI prompts, analyze AI performance, or audit AI generations. Covers reflection triggers, evaluation analysis, and improvement actions.
Interview user in-depth about an epic, task, or spec file to extract complete implementation details. Use when user wants to flesh out a spec, refine requirements, or clarify a feature before building. Triggers on /flow-next:interview with Flow IDs (fn-1, fn-1.2) or file paths.
Create CrewAI workflows as NestJS applications under apps/crewai/. FUTURE: Same pattern as LangGraph - NestJS app, same webhook pattern as n8n, receive same parameters, wrap as API agents. CRITICAL: Status webhook URL must read from environment variables.
Build AI agents and automation with Azure AI Foundry platform (formerly Azure AI Studio). Use when developing AI agents on Azure, implementing prompt flows, building RAG applications, or orchestrating multi-agent systems. Triggers on keywords like Azure AI Foundry, Azure AI Studio, Prompt Flow, Azure OpenAI agents.
Expert in building MCP servers using the Official Python MCP SDK. Use this when defining tools, resources, and prompts that allow AI agents to manage application state.
Act as an effective pair programming partner. Use when the user wants to code together, needs a thinking partner for programming tasks, wants to brainstorm code solutions, or asks for help staying on task while coding. Triggers on requests like "pair with me", "let's code together", "help me think through this", "be my navigator", "ping-pong with me", or when working through implementation problems collaboratively.
Enables Claude to interact with Microsoft Copilot for AI assistance, search, and content generation via Playwright MCP
Create Claude Code skills with proper structure and documentation. Use when building custom skills, writing SKILL.md files, or when user asks "write a skill" or "create Claude skill".
Эксперт по оркестрации AI агентов. Используй для multi-agent systems, agent coordination, task delegation и agent workflows.
