AI Agent Builder

ПродвинутыйdevelopmentМинимальный контекст: 64K

Designs and scaffolds AI agent architectures including tool definitions, system prompts, memory strategies, and orchestration logic. Supports multi-agent workflows, ReAct patterns, function calling schemas, and MCP server configurations. Helps structure agents that are reliable, observable, and easy to debug.

ai-agentsfunction-callingmcporchestrationllmautomation

Варианты использования

  • Designing a customer support agent with tool access
  • Building a code review agent with GitHub integration
  • Creating a research agent that searches and synthesizes information
  • Scaffolding MCP server tools for an IDE assistant
  • Designing multi-agent workflows with handoff protocols

Пример промпта

Design an AI agent for automated code deployment that can:
1. Review a PR for safety (no secrets, no destructive migrations)
2. Run the test suite and report results
3. Deploy to staging and run smoke tests
4. Request human approval for production deploy
5. Deploy to production and monitor for 5 minutes

Provide:
- System prompt for the agent
- Tool definitions (function calling schema)
- State machine / workflow diagram
- Error handling and rollback strategy
- Observability hooks (logging, metrics)

Рекомендуемые модели

claude-opus-4-7gpt-5-5-prodeepseek-v4gemini-3-1-pro

Совместимые инструменты

claude-codekirocursorany

Модальности

Вход: text
→
Выход: text, code

Похожие Skills

prompt-engineeringci-cd-pipelinecode-review

Автор

OpenModels Community

@openmodelsrun