openai-docs

Search and fetch official OpenAI documentation via MCP server.

Updated Feb 28, 2026
One-click install
npx skills add https://github.com/raphaelmans/agent-skills --skill openai-docs-raphaelmans
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-docs
Source: https://github.com/raphaelmans/agent-skills/tree/main/.system/openai-docs
Command: npx skills add https://github.com/raphaelmans/agent-skills --skill openai-docs-raphaelmans

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Official OpenAI docs are the authoritative source for model guidance, upgrades, and prompts, but teams often need a reliable, programmatic way to access and cite them.

Core Features & Use Cases

  • MCP-powered doc search and fetch for OpenAI guidance.
  • Reference-driven upgrade planning using latest-model, upgrading-to-gpt-5p4, and gpt-5p4-prompting-guide.
  • Safe fallback to official sources when MCP is unavailable.

Quick Start

Search the MCP server for the most relevant OpenAI docs pages, fetch exact sections, and answer with concise, cited guidance.

Frequently Asked Questions about openai-docs

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

FAQPage Schema
How do I access official OpenAI documentation programmatically for model upgrade guidance?

You access OpenAI documentation programmatically by searching the MCP server to fetch exact sections and provide cited guidance on model upgrades and prompting. It prioritizes MCP results over standard web search for OpenAI-related questions.

What is the best way to find OpenAI prompting guides and latest model references?

The best way to find OpenAI prompting guides is by loading specific references like latest-model, upgrading-to-gpt-5p4, and gpt-5p4-prompting-guide directly through the MCP server for authoritative, cited results.

How do I get cited OpenAI docs when the MCP server is unavailable?

When MCP data is unavailable, the system gracefully falls back to official OpenAI domains via web search and still cites sources. This ensures you receive accurate documentation even during connectivity issues.

Does the OpenAI docs MCP search provide authoritative guidance for model selection?

Yes, the OpenAI docs MCP search provides authoritative guidance for model selection by locating and summarizing official documentation. It fetches exact sections to deliver concise, reference-driven answers.

Can I use MCP to fetch specific sections of OpenAI documentation instead of whole pages?

Yes, you can use the MCP server to fetch exact sections of OpenAI documentation rather than whole pages. This allows you to extract precise, relevant guidance for model upgrades and prompts.

Why should I prioritize MCP results over web search for OpenAI documentation?

You should prioritize MCP results over web search because the MCP server provides authoritative, directly fetched OpenAI documentation sections. This avoids outdated or incorrect third-party information and ensures citations.