Cursor Docs Skill

An unofficial mirror of the Cursor documentation, workflows, and guides, packaged as an Agent Skill so coding agents read the docs locally instead of searching the web. A GitHub Action refreshes the mirror every 3 hours.

The skill lives in skills/cursor-docs/. The repository is also a plugin, cursor-docs, for Claude Code, Codex, and Cursor.

Install

Use

Ask a Cursor question and the agent picks up the skill on its own, or call it with a topic:

• Cursor and Claude Code: /cursor-docs hooks (as a Claude Code plugin, also /cursor-docs:cursor-docs hooks)
• Codex: $cursor-docs hooks

With no topic, the skill shows what the mirror covers. skills/cursor-docs/SKILL.md holds the instructions the agent follows.

Update

Every refresh sets the plugin version to the time of the mirror's last change (2026.1103.1534 is November 3, 15:34 UTC), so plugin managers see each update.

What's mirrored

The fetcher reads https://cursor.com/docs/sitemap.xml, https://cursor.com/sitemap.xml, and https://cursor.com/llms.txt and merges the lists, because none is complete on its own. It mirrors three sections:

• Documentation under /docs. cursor.com serves Markdown for a docs page when the request prefers it, so pages are fetched from their canonical path.
• Workflows under /workflows, converted from HTML.
• Guides under /guides, converted from HTML.

Enterprise administration (/docs/enterprise, /docs/enterprise/*, /docs/account/enterprise/*), other parts of cursor.com such as /help, /learn, and /blog, links to files such as llms.txt or openapi.yaml, and other sites are left out.

references/INDEX.md lists every page by section. references/docs_manifest.json records each page's upstream URL, content hash, and live or stale status.

Freshness guarantees

A refresh builds the whole mirror in memory and publishes it only when every check passes, so a failed run never leaves a half-written mirror. The run fails without publishing when:

• discovery finds no pages, or fewer than 80% of the pages already mirrored
• no page could be fetched live
• more than 20% of pages are stale, have no usable Markdown, or fail cleaning
• a page fails and has no earlier copy to fall back on

A page that fails while an earlier copy exists keeps that copy and is marked stale. Converted HTML pages must keep a heading and real text, so a cursor.com redesign fails the run instead of publishing empty pages.

For maintainers

python3 -m venv .venv
.venv/bin/python -m pip install -r scripts/requirements-dev.txt
.venv/bin/python -m pytest -q
.venv/bin/python scripts/fetch_docs.py

scripts/fetch_docs.py holds the Cursor settings. Everything else in scripts/, tests/, and .github/ is shared, byte for byte, with claude-code-docs-skill and codex-docs-skill; SHARED_FILES in scripts/docs_mirror.py lists the files. Change shared files in all three repositories on branches with the same name: CI's drift check (python scripts/fetch_docs.py --check-drift) compares against that branch in the other repositories, or their main, and fails while the files differ.

.
├── plugin.json                          # Agent Plugins manifest (Codex, Cursor)
├── .claude-plugin/                      # Claude Code plugin and marketplace (Codex and npx skills read these too)
├── .cursor-plugin/                      # Cursor plugin and marketplace
├── skills/cursor-docs/
│   ├── SKILL.md                         # instructions the agent follows
│   ├── agents/openai.yaml               # Codex and ChatGPT app metadata
│   └── references/                      # mirrored pages, INDEX.md, docs_manifest.json
├── scripts/
│   ├── fetch_docs.py                    # Cursor settings
│   └── docs_mirror.py                   # shared engine
├── tests/                               # offline tests
└── .github/workflows/update-docs.yml    # tests, refresh every 3 hours, drift check, failure alerts

Troubleshooting

• Docs look stale: check the latest run of Update docs mirror.
• A scheduled refresh failed: the workflow opens or updates an issue titled "Docs mirror update failures" and closes it after the next successful run.
• A page shows stale: upstream could not be reached on the last run, so the previous copy is still served.

Legal notice

• Unofficial. This is an unofficial community project. It is not affiliated with, endorsed by, or sponsored by Anysphere, Inc., the maker of Cursor.
• Documentation. The mirrored pages belong to Anysphere and are subject to Anysphere's terms. Every page names its source, and https://cursor.com/docs is the authoritative version.
• Trademarks. Cursor is a trademark of Anysphere, Inc. It is used here only to name the product the documentation describes.
• License. The MIT license covers only this repository's own code: the scripts, tests, workflow, and skill instructions. It does not cover the mirrored documentation.
• Removal requests. If you represent Anysphere and want this mirror changed or removed, open an issue and it will be handled promptly.