Index of every page on this site: llms.txt
All skills
am-will avatar

/openai-docs-skill

@9f954c3
by am.willam-will/codex-skills1k stars
60
Run it yourself

Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.

Use this Skill: https://skilld.dev/gh/am-will/codex-skills/openai-docs-skill

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈88 tokens for metadata: the name and description. ≈422 when used: this file.

Description uses 4.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈354 characters, or 4.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

OpenAI Docs MCP Skill

Overview

Use the OpenAI developer documentation MCP server from the shell to search and fetch authoritative docs. Always do this for OpenAI platform work instead of relying on memory or non-official sources.

Core rules

  • Always use this skill for OpenAI API/SDK/Apps/Codex questions or when precise, current docs are required.
  • Query the MCP server via the CLI wrapper in scripts/openai-docs-mcp.sh (do not rely on Codex MCP tools).
  • Use search or list to find the best doc page, then fetch the page (or anchor) for exact text.
  • Surface the doc URL you used in your response so sources are clear.

Quick start

scripts/openai-docs-mcp.sh search "Responses API" 5
scripts/openai-docs-mcp.sh fetch https://platform.openai.com/docs/guides/migrate-to-responses

Workflow

  1. Discover: search with a focused query. If unsure, use list to browse.
  2. Read: fetch the most relevant URL (optionally add an anchor).
  3. Apply: summarize and/or quote relevant sections; include the URL.

Script reference

The CLI wrapper is at scripts/openai-docs-mcp.sh and uses curl + jq against https://developers.openai.com/mcp.

Subcommands:

  • init: initialize and inspect server capabilities.
  • tools: list available tools on the MCP server.
  • search <query> [limit] [cursor]: return JSON hits from the docs index.
  • list [limit] [cursor]: browse docs index.
  • fetch <url> [anchor]: return markdown for a doc page or section.
  • endpoints: list OpenAPI endpoints.
  • openapi <endpoint-url> [lang1,lang2] [code-only]: fetch OpenAPI schema or code samples.

Environment:

  • MCP_URL: override the default MCP endpoint.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warnings2mo5 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill provides a command-line utility to query and retrieve official OpenAI developer documentation via an MCP server. It uses standard system tools like curl and jq to fetch authoritative information from a trusted source.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

  • Runlayer9mo

    2/2 files flagged

  • ZeroLeaks7mo

    1 finding · Score: 69/100

Signed by skilld at 9f954c3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 10 months ago

README badge

README badge for am-will/codex-skills/openai-docs-skill

Queries the OpenAI developer documentation via MCP server using shell commands (curl/jq) to search, fetch, and browse official guides, API schemas, SDKs, and migration docs. Use this skill whenever a task involves the OpenAI API, Chat Completions, Realtime, or other OpenAI platform features that require current official documentation.

Generated from the current SKILL.md.

Does this skill cover the OpenAI API, SDKs, and ChatGPT Apps SDK?
Yes. The skill queries OpenAI's official developer docs and covers the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, endpoint schemas, parameters, limits, and migrations.
How do I search the OpenAI docs?
Use the `scripts/openai-docs-mcp.sh` wrapper with `search <query>` to find relevant doc pages, then `fetch <url>` to retrieve the full markdown content.
Can I fetch a specific section or anchor within a doc page?
Yes. The `fetch` command accepts an optional anchor parameter to retrieve a specific section of a doc page.
What should I do if I need OpenAPI endpoint details or code samples?
Use the `endpoints` subcommand to list OpenAPI endpoints, or `openapi <endpoint-url>` to fetch the schema or code samples in specific languages.
Can I override the default MCP endpoint?
Yes. Set the `MCP_URL` environment variable to override the default endpoint at `https://developers.openai.com/mcp`.

Generated from the current SKILL.md. These answers refresh after source changes.