Openai Knowledge

This skill ensures Claude pulls real OpenAI documentation instead of guessing at API parameters, rate limits, or schema details. It connects to the OpenAI Developer Documentation MCP server to search and fetch exact markdown pages, then answers based on that text. You'd reach for this when working with the Responses API, Realtime API, streaming, tools, or any platform feature where precision matters. If the MCP server isn't configured, it walks you through setup via CLI or config file. The workflow is straightforward: check if the docs tools are available, search and fetch the relevant pages, then quote the actual documentation. It's a forcing function to stop hallucinating OpenAI specs.

skills.sh installs: 453
GitHub stars: 30.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add openai/openai-agents-python --skill openai-knowledge --agent claude-code

Installs into .claude/skills of the current project.

Files

OpenAI Knowledge

Overview

Use the OpenAI Developer Documentation MCP server to search and fetch exact docs (markdown), then base your answer on that text instead of guessing.

Workflow

1) Check whether the Docs MCP server is available

If the mcp__openaiDeveloperDocs__* tools are available, use them.

If you are unsure, run codex mcp list and check for openaiDeveloperDocs.

2) Use MCP tools to pull exact docs

Search first, then fetch the specific page or pages.
- mcp__openaiDeveloperDocs__search_openai_docs → pick the best URL.
- mcp__openaiDeveloperDocs__fetch_openai_doc → retrieve the exact markdown (optionally with an anchor).
When you need endpoint schemas or parameters, use:
- mcp__openaiDeveloperDocs__get_openapi_spec
- mcp__openaiDeveloperDocs__list_api_endpoints