Skip to main content
affpapa.org
RU EN
skill CX Codex

openai-docs-skill — Codex skill: OpenAI docs from the shell

Pulls current OpenAI developer documentation through an MCP server without leaving the terminal. Handy when the agent writes Responses API or SDK code and guessing parameters is not an option.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add am-will/codex-skills --skill openai-docs-skill -a claude-code
Open on GitHub

What openai-docs-skill does

The skill points the agent at official OpenAI docs instead of letting it work from memory or random blog posts. A shell wrapper at scripts/openai-docs-mcp.sh talks to https://developers.openai.com/mcp using curl and jq. Codex MCP tools are skipped on purpose; every call comes from the command line.

The loop is short. Run search with a narrow query, or list to skim the index, then fetch the page you picked, optionally with an anchor for one section. Two more subcommands cover API work: endpoints lists OpenAPI endpoints, openapi returns a schema or code samples for one of them. The agent is told to show the doc URL it relied on.

curl and jq have to be installed, otherwise the wrapper has nothing to run. The endpoint is configurable through MCP_URL if you need a different host. Note the distinction: this is a skill that queries a remote MCP server over HTTP, not a server you register yourself.

What it helps with

  • confirm an endpoint schema before the agent writes the request
  • locate the migration guide from Chat Completions to Responses
  • check parameter and limit details in the official docs index
  • grab an OpenAPI schema plus code samples for one endpoint
  • verify SDK or Apps SDK behaviour instead of trusting recall

Example prompts for the agent

  • Search the OpenAI docs for the Realtime API and list the required session parameters.
  • Fetch the OpenAPI schema for this endpoint and show a Python request example.
  • Check the official guide on moving from Chat Completions to Responses and cite the page.

How to install openai-docs-skill

1Skills CLI (Vercel)

npx skills add am-will/codex-skills --skill openai-docs-skill -a claude-code

2Manually: put the files in place

~/.claude/skills/openai-docs-skill/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/openai-docs-skill/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about openai-docs-skill

How do I install Anthropic-docs-skill in Claude Code?

Run npx skills add am-will/codex-skills --skill openai-docs-skill -a claude-code. The skill lands at ~/.claude/skills/openai-docs-skill/SKILL.md.

What does openai-docs-skill do?

It makes the agent search and read OpenAI developer documentation through an MCP server from the shell, then cite the page it used. The scope covers the API, SDKs, ChatGPT Apps SDK, Codex and MCP integrations.

What does the skill need to run?

curl and jq, since the wrapper script is built on both. The MCP endpoint has a default and can be overridden with the MCP_URL variable.

Similar skills

Everything for AI and ML →
skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 349,800installs

From the same set13

Frontend Responsive Design Standards A skill that gives your coding agent rules for mobile-first layouts: breakpoints, relative units, touch targets and content priority. CX Codex +1 1,200installs role-creator Builds and updates Codex subagent definitions as standalone TOML files. Useful when you need isolated role configs with explicit model settings and developer instructions. CX Codex +1 1,200installs swarm-planner Builds implementation plans that show task dependencies for parallel agent work. Use it before coding changes in an unfamiliar codebase. CX Codex +1 1,200installs gemini-computer-use Runs Gemini 2.5 Computer Use agents with Playwright to drive browser workflows. It captures screenshots, calls UI actions, and prompts for confirmation on risky steps. CX Codex +1 1,200installs llm-council This skill runs several CLI agents as independent planners, strips their identities, and merges the results into one final plan. Useful when a single model's bias is the problem. CX Codex +1 1,200installs Agent Browser A skill that hands your agent a Rust-based headless browser: navigate, click, fill forms and snapshot pages through structured commands. CX Codex +1 1,200installs plan-harder Turns complex requests into structured sprint plans with atomic tasks. Triggers when you tell the agent to plan harder, focusing purely on architecture and risks. CX Codex +1 1,200installs parallel-task This skill reads a development plan and assigns ready tasks to subagents in parallel. Use it to follow task dependencies and keep progress recorded in the plan. CX Codex +1 1,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor