docs-editor

作成者: openai

OpenAI Cookbookのノートブック、Markdown、MDXをレビュー・編集し、技術的正確性、明確さ、文法、一貫性、実行可能な例、リポジトリ…を確認します。

npx skills add https://github.com/openai/openai-cookbook --skill docs-editor

OpenAI Cookbook docs editor

Objective

Review Cookbook content conservatively. Improve correctness and readability without changing the author's intent, inventing facts, or creating unrelated churn.

Workflow

1. Define the scope

  • Prefer explicit paths or the files changed in the pull request.
  • For pull requests, review changed .md and .mdx files plus Markdown cells in changed .ipynb files.
  • Review registry.yaml and authors.yaml when content is added, moved, removed, or attributed to a new author.
  • Stay within the requested content. Do not turn a focused review into a repository-wide rewrite.

2. Protect notebook integrity

  • When the request is editorial, edit only notebook Markdown cells.
  • Preserve code cells, outputs, execution counts, attachments, cell order, cell IDs, and notebook and cell metadata.
  • Avoid reserializing an entire notebook for a small prose change. Inspect the diff for unintended JSON churn.
  • Do not execute notebook code unless the user requests it or code changes are in scope. Markdown-only edits require structural validation, not calls to external services.
  • Never add hard-coded secrets. Document required environment variables such as OPENAI_API_KEY.

3. Review the content

Load resources/style-guide.md and check:

  • Technical claims, API names, model names, identifiers, commands, paths, and URLs.
  • Agreement between prose, code, sample inputs, and expected outputs.
  • Prerequisites, dependencies, environment variables, and steps needed to run an example.
  • File and notebook names, headings, lists, numbering, cross-references, and links.
  • Grammar, spelling, punctuation, terminology, capitalization, and concise wording.
  • Publication metadata in registry.yaml and author metadata in authors.yaml when applicable.

Verify uncertain technical claims from an authoritative source or flag them for review. Do not guess.

4. Prioritize findings

Use the repository's review bar:

  • P0: Broken notebook JSON; hard-coded secrets; materially false or unsafe guidance; or any repository-defined P0 issue, including naming violations, typos, broken links, inconsistent formatting, placeholder identifiers, undocumented environment variables, or out-of-sync publication metadata.
  • P1: Misleading instructions, prose that contradicts code or output, missing prerequisites, or a required link that does not work.
  • P2: Clear improvements to grammar, consistency, organization, or readability that do not affect correctness.
  • P3: Optional polish with little effect on comprehension.

5. Make safe edits

  • Fix obvious typos, grammar, punctuation, broken local references, and clear prose/code mismatches.
  • Keep changes minimal, local, and reversible.
  • Preserve exact literals, code identifiers, commands, values, counts, conditions, modality, negation, and uncertainty markers.
  • Tighten prose only when meaning stays unchanged. Prefer concrete nouns, strong verbs, short introductions, and direct instructions.
  • Flag any change that depends on product knowledge or could alter meaning instead of guessing.
  • Do not make file-wide formatting or stylistic changes solely for uniformity.

6. Validate the result

For any changed notebook, run the repository validator:

env -u VIRTUAL_ENV uv run --with nbformat python .github/scripts/check_notebooks.py

Then:

  • Run git diff --check.
  • Inspect the diff and confirm that notebook changes are limited to intended Markdown cells.
  • Run an available YAML linter if registry.yaml or authors.yaml changed.
  • Run the relevant example or test only when executable content changed and its dependencies are available.

7. Report the review

Provide:

  • A short summary of the scope and edits.
  • Auto-fixed items.
  • Remaining findings grouped by priority with file and cell or line references.
  • The validation commands run and their results.

If no issues remain, say so explicitly.

openaiのその他のスキル

release
openai
コミットされたバージョンを更新して Symphony リリースを切り、それをコミットし、マージされたコミットにタグを付け、Burrito リリースワークフローを確認します。求められた際に使用します…
signing-entitlements
openai
macOSアプリの署名、権限、ハード化されたランタイム、Gatekeeperの問題を検査します。コード署名の失敗や権限の欠落などの診断を求められた際に使用します。
building-ai-agent-on-cloudflare
openai
Cloudflare上でAgents SDKを使用してAIエージェントを構築し、状態管理、リアルタイムWebSocket、スケジュールタスク、ツール統合、チャットなどを実現します。
epigraphdb-skill
openai
オントロジー、文献、MR、遺伝子-薬剤、サポートパスエビデンスに関するコンパクトなEpiGraphDB APIリクエストを送信します。ユーザーが簡潔なEpiGraphDBサマリーを希望する場合に使用します。
runtime-behavior-probe
openai
一時的なプローブスクリプト、検証マトリックス、状態制御、および発見事項優先のレポートを用いて、ランタイム動作調査を計画・実行します。以下の場合にのみ使用してください…
deep-security-scan
openai
ユーザーがリポジトリ全体またはスコープ指定パスに対する深く網羅的な、マルチパスまたはバリアンス低減型のCodexセキュリティスキャンを求めた場合に使用します。独立した反復実行を複数回行います…
define-security-policy
openai
リポジトリまたはコンポーネントのSECURITY.mdガイダンスを定義、レビュー、または更新します。ユーザーがCodex Securityがレビューすべき内容、対象外の内容を明確にしたい場合に使用します。
validation
openai
Codexがセキュリティスキャンの検証段階にすでにある場合、またはユーザーが1つ以上の候補となるセキュリティ findings が…かどうかを判断するよう明示的に求めた場合に使用します。