openai/openai-knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
npx skills add https://github.com/openai/openai-agents-python --skill openai-knowledge
Use the OpenAI Developer Documentation MCP server to search and fetch exact docs (markdown), then base your answer on that text instead of guessing.
If the mcp__openaiDeveloperDocs__* tools are available, use them.
If you are unsure, run codex mcp list and check for openaiDeveloperDocs.
mcp__openaiDeveloperDocs__search_openai_docs → pick the best URL.mcp__openaiDeveloperDocs__fetch_openai_doc → retrieve the exact markdown (optionally with an anchor).mcp__openaiDeveloperDocs__get_openapi_specmcp__openaiDeveloperDocs__list_api_endpointsBase your answer on the fetched text and quote or paraphrase it precisely. Do not invent flags, field names, defaults, or limits.
Provide one of these setup options, then ask the user to restart the Codex session so the tools load:
codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp~/.codex/config.toml): [mcp_servers.openaiDeveloperDocs]
url = "https://developers.openai.com/mcp"
Also point to: https://developers.openai.com/resources/docs-mcp#quickstart
Take openai/openai-knowledge from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.