Openai Docs
ListedAccess and query OpenAI's official documentation directly through this davila7 agent for accurate API usage and model details.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add davila7/claude-code-templates --skill openai-docs -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
davila7
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.
No undeclared network calls: failed
Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: developers.openai.com.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
Hosts contacted
developers.openai.comundeclaredWhat it found
- cli-tool/components/skills/ai-research/openai-docs/agents/openai.yaml:14contacts developers.openai.com
url: "https://developers.openai.com/mcp"
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned davila7/claude-code-templates at 79182c51fb.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 79182c51fb
- Scanned
- 3 files, 73 lines
About this skill
What it does
This skill provides direct access to and querying capabilities for OpenAI's official developer documentation through a Model Context Protocol (MCP) server. It allows AI agents to retrieve accurate API usage information, model details, and guidance directly from developers.openai.com, prioritizing this source over general web searches for all OpenAI-related inquiries.
When to use it
- When needing precise information about the Chat Completions API, Codex, or other OpenAI products like the Agents SDK.
- To understand how to build ChatGPT apps using the Apps SDK and Responses API.
- When troubleshooting issues related to OpenAI's Realtime API or gpt-oss models.
- To find specific sections of documentation for a particular task or feature.
Key capabilities
mcp__openaiDeveloperDocs__search_openai_docs: Searches the OpenAI developer documentation for relevant pages.mcp__openaiDeveloperDocs__fetch_openai_doc: Retrieves specific sections and accurately quotes/paraphrases content from the documentation.mcp__openaiDeveloperDocs__list_openai_docs: Allows browsing or discovering documentation pages without a specific query.- Prioritizes OpenAI developer docs over web search for accuracy.
Example prompts
- "How do I use the Chat Completions API?"
- "What are the capabilities of the Codex model?"
- "Show me the documentation on building ChatGPT apps with the Apps SDK."
- “List available documents related to the Agents SDK.”
Tips & gotchas
- The skill relies on a functioning MCP server (
openaiDeveloperDocs). If unavailable, it will attempt installation automatically. If that fails, an escalated permission request will be made before user intervention is requested. - Always prioritize results from the MCP tools over web searches for OpenAI-related questions.
- When answering, cite documentation sources and provide code snippets only when supported by the official docs.