Skip to content
Back to skills

Openai Docs

ASecurity

查 OpenAI 官方文档。查 OpenAI 产品/API、Codex 配置、模型、skill 的一手资料,疑难杂症以官方为准。

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 16, 2026
ai-agentsapidocumentation

Works with

  • api
  • mcp

Security analysis

A100/100

Pro scans all 17 files and shows the line behind each finding

Scanned October 16, 2026

npx -y skills add 0mlkrizzz655335v/claude-skills-zh --skill openai-docs --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Openai Docs?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Openai Docs
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/0mlkrizzz655335v-openai-docs/badge)](https://www.skillsdirectory.com/skills/0mlkrizzz655335v-openai-docs)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "openai-docs"
description: "查 OpenAI 官方文档。查 OpenAI 产品/API、Codex 配置、模型、skill 的一手资料,疑难杂症以官方为准。"
metadata:
  short-description: "Official OpenAI docs and Codex guidance"
---

# OpenAI Docs

Provide current, cited OpenAI product, API, model, and Codex guidance.

## Establish the needed evidence

- For local setup or troubleshooting, inspect the relevant local state first. Consult official documentation for unresolved product behavior and changing facts. A documentation lookup should not delay an otherwise supported local repair or backup.
- For documentation questions, use an available official search/retrieval tool, or official-domain web search. If the user supplied a specific official URL, open it directly. Read the actual relevant page before citing it; do not rely on a search snippet.
- Preserve explicitly requested models, products, and scope. If the first source is insufficient, retrieve the next relevant official source.
- For a simple factual answer, use the fetched source directly; open route references only when they add information the task needs. Prefer `learn.chatgpt.com` for ChatGPT Work.

## Choose one primary route

Choose the relevant route; read its reference only when the task needs the specialized workflow:

- **Explicitly requested local documentation integration:** Read [integration guidance](references/mcp-diagnostics.md) only when the user explicitly requests that local integration.
- **Model migration, upgrades, or model-specific prompting:** Read [model-migration.md](references/model-migration.md) for actual migration planning, implementation, dynamic target resolution, or prompt changes. Preserve an explicitly requested target.
- **Model selection and comparisons:** Read [model-selection.md](references/model-selection.md) only when nuanced current, latest, default, cost, latency, quality, or modality tradeoffs need more guidance. Do not run a migration resolver for selection alone.
- **Product, API, ChatGPT Work, and mixed Chat/Work/Codex documentation:** Read [official-docs.md](references/official-docs.md) only when fetched official pages leave source selection, API schemas, or the requested implementation unresolved. This route is not manual-first.
- **Explicitly broad Codex setup, orientation, or cross-topic synthesis:** Read [codex-self-knowledge.md](references/codex-self-knowledge.md) when the eligible Codex manual or deeper Codex procedures are needed.

Start with the relevant reference. Read additional references or run helpers only to resolve a concrete remaining question; do not load every route by default.

## Source and execution boundaries

- Search, open, fetch, and cite only `developers.openai.com`, `platform.openai.com`, and `learn.chatgpt.com`. Cite the page that supports the claim. State uncertainty when official sources do not establish pricing, availability, account access, limits, or behavior.
- Preserve an explicitly requested model for selection, migration, and prompting. Resolve an unspecified latest or current migration target only after searching and fetching current official guidance.
- Use `references/latest-model.md` only as a disclosed fallback after current official model guidance does not answer the question. Read `references/upgrading-to-gpt-6-astra.md` only for an actual, requested GPT-6 migration; read `references/prompting-guide.md` only for requested prompting work.
- Before an operation that actually requires authenticated OpenAI API access, use `openai-platform-api-key` when available. Local code edits, offline tests, documentation, conceptual examples, and model selection do not by themselves require credentials. Do not start a credential-setup flow unless the requested operation needs it.
- Say "OpenAI Docs" or "official OpenAI documentation" in user-facing answers. Keep exact official citations and examples concise.

Files in this skill

  • LICENSE.txt10.7 KB
  • SKILL.md3.8 KB
  • agents/openai.yaml376 B
  • assets/openai-small.svg1.1 KB
  • assets/openai.png1.4 KB
  • references/codex-self-knowledge.md7.3 KB
  • references/latest-model.md2.1 KB
  • references/mcp-diagnostics.md2.3 KB
  • references/model-migration.md5 KB
  • references/model-selection.md1.3 KB
  • references/official-docs.md3.3 KB
  • references/prompting-guide.md10 KB
  • references/upgrade-guide.md1 KB
  • references/upgrading-to-gpt-6-astra.md18.8 KB
  • scripts/fetch-codex-manual.mjs16.3 KB
  • scripts/resolve-latest-model-info1.1 KB
  • scripts/resolve-latest-model-info.cjs4 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.