docs-sync
This skill audits and updates English SDK documentation by comparing implementation against docs, identifying gaps and inaccuracies using code evidence.
Identity proven by GitHub's verified organisation badge (openai)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
- License
- MIT (permissive)
- Pin
- 05241c7pinned Oct 9, 2026
- Context cost
- about 1,400 tokenswhen the skill loads
- GitHub stars
- 3,899on openai/openai-agents-js
- Scripts
- None found
What it does
“Audit or update authored English SDK documentation within a requested topic or diff using implementation evidence.”
Generated summary from the skill's own text
This skill audits and updates English SDK documentation by comparing implementation against docs, identifying gaps and inaccuracies using code evidence. It works within a requested topic or code diff, applying the repository's documentation release policy before proposing or completing authorized changes.
When to use it
- Audit documentation coverage against current implementation code
- Identify outdated or missing feature descriptions in docs
- Update docs when code changes or new features land
- Verify documentation matches public API surface
When not to
- Updating translated documentation in non-English languages
- Making documentation changes without implementation evidence
- Editing documentation outside the designated docs directory structure
Install
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add openai/openai-agents-js --skill docs-syncInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install openai/openai-agents-js docs-sync@05241c7aa3d5629acc7407dd8ee1105637fe0369Installs the commit we checked (05241c7).
Copy by hand
Download the folder at 05241c7 and put it in .claude/skills/docs-sync for Claude Code and in .agents/skills/docs-sync for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "docs-sync" by OpenAI. Source, pinned to commit 05241c7aa3d5629acc7407dd8ee1105637fe0369: https://github.com/openai/openai-agents-js/tree/05241c7aa3d5629acc7407dd8ee1105637fe0369/.agents/skills/docs-sync 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/docs-sync/ for Claude Code and .agents/skills/docs-sync/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Listing and checks: https://www.agentnative.dev/skills/openai/docs-sync
SKILL.md at the pin
--- name: docs-sync description: Audit or update authored English SDK documentation within a requested topic or diff using implementation evidence. --- # Docs Sync ## Overview Identify documentation gaps and inaccuracies within the requested topic or diff using implementation evidence. ## Scope and authorization For audit or proposal-only requests, report findings without editing. When the user requests updates or has approved a plan, complete the scoped edits and verification without asking again. Ask only for unresolved behavior, scope, release timing, or additional authority. Apply the repository's Documentation Release Timing policy before including unreleased behavior in `docs/`. ## Workflow 1. Confirm scope and base branch - Identify the current branch and default branch (usually `main`). - Prefer analyzing the current branch to keep work aligned with in-flight changes. - Use a branch diff only for a branch-scoped request. A requested topic or released-doc correction remains in scope even when unrelated to the current branch diff. - Avoid switching branches if it would disrupt local changes. Prefer read-only inspection such as `git show main:<path>`. If a separate checkout is genuinely required, stop and obtain the explicit approval required by `AGENTS.md` before creating or switching a worktree. 2. Build a feature inventory from the selected scope - Bound the inventory to the requested topic or diff. Inventory the full surface only for an explicitly comprehensive audit. - For branch-scoped work, inspect additions, changes, and removals relative to the intended base. - Focus on user-facing behavior: public exports, configuration options, environment variables, CLI commands, default values, and documented runtime behaviors. - Capture evidence for each item (file path + symbol/setting). - Use targeted search to find option types and feature flags (for example: `rg "Options"`, `rg "process.env"`, `rg "export"`). - When the topic involves OpenAI platform features, invoke `$openai-knowledge` to pull current details from the OpenAI Developer Docs MCP server instead of guessing, while treating the SDK source code as the source of truth when discrepancies appear. - For MCP SDK (`modelcontextprotocol/typescript-sdk`) or Vercel AI SDK (`@ai-sdk/*`) topics, optionally use Deepwiki MCP for quick lookups, and still treat the SDK source code as the source of truth. 3. Doc-first pass: review existing pages - Walk each relevant page under `docs/src/content/docs` (excluding `docs/src/content/docs/openai`). - Identify missing mentions of important, supported options (opt-in flags, env vars), customization points, or new features from `packages/`. - Propose additions where users would reasonably expect to find them on that page. 4. Code-first pass: map features to docs - Review the current docs information architecture under `docs/src/content/docs`. - Determine the best page/section for each feature based on existing patterns and package boundaries. - Identify features that lack any doc page or have a page but no corresponding content. - Note when a structural adjustment would improve discoverability. 5. Detect gaps and inaccuracies - **Missing**: features/configs present in main but absent in docs. - **Incorrect/outdated**: names, defaults, or behaviors that diverge from main. - **Structural issues** (optional): pages overloaded, missing overviews, or mis-grouped topics. 6. Classify the proposed complete diff - Use the Documentation Change Verification Tiers in `AGENTS.md` as the single source of truth. - Classify the complete proposed diff by its highest applicable Editorial, Content, or Structural tier before editing. - Keep the tier-specific verification separate from the existing eligibility rules for `$implementation-final-review`, `$code-change-verification`, `$changeset-validation`, and `$pr-draft-summary`. 7. Report findings or continue authorized updates - For audit-only work, provide evidence, suggested locations, proposed edits, and required verification, then stop. - For an update request, complete the authorized edits using the findings and selected verification tier. 8. Apply authorized changes (English only) - Edit only English docs in `docs/src/content/docs/**`. - Exclude `docs/src/content/docs/openai` from review and updates. - Do **not** edit `docs/src/content/docs/ja`, `docs/src/content/docs/ko`, or `docs/src/content/docs/zh`. - Keep changes aligned with the existing docs style and navigation. - Do not add TypeScript or TSX fenced blocks directly to MDX. Place every TypeScript or TSX snippet in a compilable source file under `examples/docs/<doc-area>/`, import it into MDX with `?raw`, and render that imported source using the existing docs pattern. - If code is not useful enough to maintain as a complete example, explain the behavior in prose instead of adding an unverified snippet. - Run the focused verification required by the highest applicable Documentation Change Verification Tier in `AGENTS.md`. When the complete diff changes a rendered TypeScript or TSX snippet source or its MDX import/rendering, run `pnpm -F docs-code build-check` and fix issues before handoff. ## Output format Use this template when reporting findings: Docs Sync Report - Doc-first findings - Page + missing content → evidence + suggested insertion point - Code-first gaps - Feature + evidence → suggested doc page/section (or missing page) - Incorrect or outdated docs - Doc file + issue + correct info + evidence - Structural suggestions (optional) - Proposed change + rationale - Proposed edits - Doc file → concise change summary - Unresolved decisions, only when needed ## References - `references/doc-coverage-checklist.md`
From openai/openai-agents-js at 05241c7, shown as plain text under its license: MIT (permissive). The license text is in LICENSE.
View SKILL.md on GitHub at 05241c7Files
- SKILL.md5.8 KB · 5542ef9e7bcd
- agents/
- openai.yaml232 B · 2e62bee17a95
- references/
- doc-coverage-checklist.md2.9 KB · 484952910c23
3 files, 8.9 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at 05241c7More from OpenAI
code-change-verification
Runs formatting, linting, type checking, and test verification for SDK code changes after review.
Contains scripts
Codex · about 1.3K tokens · pinned 6 days ago
docs-sync
This skill audits English SDK documentation by comparing features and configuration options in the codebase against the current docs, then proposes or…
Claude Code, Codex, Cursor +4 · about 1.2K tokens · pinned 6 days ago
examples-run-analysis
Analyzes logs and artifacts from manual examples runs to validate example behaviors, identify failures, and classify issues.
Claude Code, Codex, Cursor +4 · about 1K tokens · pinned 6 days ago
final-release-review
Audits Python SDK release candidates or plans against the previous release, comparing diffs for regressions, API changes, and version compatibility.
Contains scripts
Claude Code, Codex, Cursor +3 · about 5.4K tokens · pinned 6 days ago
implementation-final-review
This skill guides agents through a structured review process for completed implementation changes before final verification.
Contains scripts
Claude Code, Codex, Cursor +3 · about 1.9K tokens · pinned 6 days ago
implementation-kickoff
This skill manages an isolated implementation workflow using a dedicated git worktree, keeping the user's original checkout unchanged while building a…
Contains scripts
Codex · about 2.9K tokens · pinned 6 days ago
Related in Docs and writing
n8n-docs-assistant
This skill answers questions about n8n configuration, setup, credentials, nodes, and troubleshooting by retrieving information from current n8n documentation.
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 450 tokens · pinned 6 days ago
algodocs-automation
This skill automates Algodocs document processing tasks through Composio's toolkit via the Rube MCP server.
by ComposioOfficial publisher
Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 6 days ago
remotion-docs
This skill enables agents to search and retrieve Remotion documentation via the Algolia API and fetch pages as Markdown.
by RemotionOfficial publisher
Claude Code, Codex, Cursor +3 · about 320 tokens · pinned 6 days ago
remotion-docs
This skill searches the Remotion documentation using the Algolia API and retrieves documentation pages as Markdown.
by RemotionOfficial publisher
Claude Code, Codex, Cursor +3 · about 320 tokens · pinned 6 days ago
receipts
This skill generates a personal Claude Code usage report from local session transcripts stored in ~/.claude/projects, mining activity across projects without…
by AnthropicOfficial publisher
Contains scripts
Claude Code · about 4.1K tokens · pinned 6 days ago
solo
This skill enables an agent to work through a single difficult mathematics problem independently within one session.
by AnthropicOfficial publisher
Claude Code · about 1.4K tokens · pinned 6 days ago
Open roles at OpenAI
5 of 242 open roles on the jobs board
- Software Engineer, Productivity - Networking
San Francisco, California, United States
- Networking Operating System Firmware Engineer
San Francisco, CA, United States (Hybrid)
- Software Engineer, Private Computing
San Francisco, California, United States (Hybrid)
- Data Center Hardware Quality & Reliability Engineer
San Francisco, California, United States (Remote)
- Software Engineer, Habitat (Online Data)
Seattle