skills.rest
jezweb
jezwebCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

openai-responses

Create stateful AI applications using OpenAI's Responses API with built-in tools and MCP integration.

961|99|Updated Oct 20, 2025
Search Tags:#openai#agentic workflows#responses api#mcp integration#reasoning preservation#stateful ai
One-click install
npx skills add https://github.com/jezweb/claude-skills --skill openai-responses
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openai-responses
Source: https://github.com/jezweb/claude-skills/tree/main/skills/openai-responses
Command: npx skills add https://github.com/jezweb/claude-skills --skill openai-responses

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the complexity of building agentic AI applications by providing comprehensive knowledge of OpenAI's Responses API - the stateful successor to Chat Completions.

Core Features & Use Cases

  • Stateful Conversations: Automatic state management with 40-80% better cache utilization.
  • Reasoning Preservation: Maintains model's thought process across turns for 5% better performance.
  • Built-in Tools: Server-side Code Interpreter, File Search, Web Search, and MCP server integration.
  • Use Case: When building customer support agents that remember conversation history, or data analysis tools that build on previous calculations.

Quick Start

Use the openai-responses skill to create a stateful AI agent that can handle multi-turn conversations while preserving reasoning state.

Quick Start

Create a stateful conversation with automatic reasoning preservation:

const conv = await openai.conversations.create(); const response = await openai.responses.create({ model: 'gpt-5', conversation: conv.id, input: 'Analyze this quarterly report and identify key trends.

Then follow up with:

Now analyze how these trends compare to the previous quarter.

Frequently Asked Questions about openai-responses

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build stateful AI agents with OpenAI's Responses API?▼

The Responses API enables stateful AI agents by automatically managing conversation state via conversation IDs, preserving reasoning across turns, and providing server-side tool hosting. Create a conversation, then pass its ID to responses.create() with your input to maintain context and reasoning state between turns.

What's the difference between OpenAI's Responses API and Chat Completions?▼

Responses API replaces Chat Completions with stateful conversations, automatic reasoning preservation, built-in tools (Code Interpreter, File Search, Web Search), MCP server integration, and 40-80% better cache utilization. It handles tool calling server-side and maintains conversation history automatically.

Can I integrate MCP servers with OpenAI's Responses API?▼

Yes. Responses API supports MCP server integration alongside built-in tools like Code Interpreter, File Search, and Web Search. This enables custom tool capabilities within stateful agentic workflows without client-side tool management.

How do I migrate from Chat Completions to Responses API?▼

Migrate by replacing chat.completions.create() with responses.create(), introducing conversation IDs for state management, and letting the API handle tool calling server-side. Responses API manages reasoning preservation and conversation context automatically.

Do I need to manage conversation history manually with Responses API?▼

No. Responses API handles automatic state management through conversation IDs. Pass the conversation ID to each responses.create() call, and the API maintains history and reasoning state without manual message tracking.

What tools are built into OpenAI's Responses API?▼

Built-in tools include Code Interpreter for computation, File Search for document retrieval, Web Search for real-time information, and MCP server integration for custom tools. All execute server-side within stateful conversations.

Related Skills

Explore More Software Engineering Skills→
takashabetakashabe
4

gemini-interactions-api

Orchestrate stateful Gemini Interactions conversations on the Gemini Enterprise Agent Platform.

Community
Intermediate
muratcankoylanmuratcankoylan
17.7k

bdi-mental-states

Translate agent cognition prompts into RDF-based BDI mental states linked to world states.

Community
Advanced
GGPromptsGGPrompts
6

docker-mcp

Discover and provision MCP servers on-demand during conversations.

Community
Advanced
Scheune10-codingScheune10-coding

llm-framework-advisor

Recommend LLM agent frameworks based on use case and decision criteria.

Community
Advanced