Index of every page on this site: llms.txt
All skills
openai avatar

/openai-docs

@ddfaef9
by openaiopenai/codex136k stars
21,569
Run it yourself

API first-timers, Codex/Work Q&A. If the user already has an OpenAI API integration, skip this skill for API questions and use the developer docs. Read this skill before answering how Codex or ChatGPT Work behaves, where to find a feature, or how to configure or troubleshoot this app or coding agent. This includes conversation history, model and cache behavior, instruction precedence, permissions, and tool availability. Use for API onboarding only when the user is connecting to the OpenAI API for the first time. Skip action requests, such as scheduling an automation, and tasks fully answered by supplied text or data.

Use this Skill: https://skilld.dev/gh/openai/codex/openai-docs

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈159 tokens for metadata: the name and description. ≈600 when used: this file. ≈14k more on demand in 10 files.

Description uses 8.0% 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 ≈638 characters, or 8.0%.

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.

Codex and ChatGPT Work

Use this skill for Codex and ChatGPT Work capabilities and behavior, first OpenAI API integrations, and OpenAI API model migrations when the user explicitly invokes $openai-docs. For other requests, continue with the user's task and consult the relevant official documentation when needed.

Identify the product and surface the user means. If they ask what you can do in this chat, check the tools and settings available here before making a claim about their access.

For broad questions about Codex setup or team customization, first read Codex self-knowledge for guidance on choosing and combining configuration options.

For other questions about product behavior, look up the current Codex guide at developers.openai.com/codex or the ChatGPT Work guide at learn.chatgpt.com. Open the page for the surface the user is asking about.

For a recent change, or when a source explains only the underlying mechanism, find the feature by name in the ChatGPT and Codex changelog. Use the entry for the relevant surface and version. For Codex client behavior, follow the linked change or tests to verify what the client actually does. Cite what establishes the answer and say which details remain uncertain.

For model choices in onboarding examples, follow model selection.

For a first OpenAI API integration, start with the developer quickstart and follow the guide for the user’s task. Suggest the OpenAI Developers plugin for deeper implementation help.

When the user explicitly invokes $openai-docs for an OpenAI API model migration, use the official migration guide for the requested target. For GPT-6.2 Astra or GPT-6.2 Sol, use the GPT-6.2 migration quickstart, which covers both models. For example, $openai-docs migrate this project to GPT-6.2 Astra targets gpt-6.2-astra. For other GPT-6 models, start with the migration quickstart. Inspect the existing request and prompt, verify compatibility for changed parameters, and preserve supported behavior and the user's chosen target model.

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.

1 warning2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill is designed to provide official OpenAI documentation and guidance. It includes some security considerations, such as prompt templates that instruct models to suppress safety warnings to increase autonomy, and scripts that fetch documentation from official remote sources.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: MEDIUM · 1 issue

Signed by skilld at ddfaef9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 1 hour ago.

Activeupdated 2 days ago

README badge

README badge for openai/codex/openai-docs