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`.
Install
Install this Claude and Codex skill with the command below. The command stays visible even when copy support is unavailable.
git clone https://github.com/openai/openai-agents-python /tmp/openai-agents-python && ln -s /tmp/openai-agents-python/.agents/skills/openai-knowledge ~/.claude/skills/openai-knowledgeFrom README
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 mcpopenaiDeveloperDocs 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. mcpopenaiDeveloperDocssearchopenaidocs → pick the best URL. mcpopenaiDeveloperDocsfetchopenaidoc → retrieve the exact markdown (optionally with an anchor). When you need endpoint schemas or parameters, use: mcpopenaiDeveloperDocsgetopenapispec mcpopenaiDeveloperDocslistapiendpoints Base your answer on the fetched text and quote or paraphrase it precisely. Do not invent flags, field names, defaults, or limits.
More from this repo
code-change-verification
Used to run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the...
credit-note-fixer
Used to fix the tiny credit-note formatting bug and rerun the exact targeted test command.
csv-workbench
Used to analyze CSV files in /mnt/data and return concise numeric summaries.