google-docs
An agent skill by cursor, from cursor/plugins. Tags: copy-editing, documentation, documents, office, writing.
What it does
Author and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers. Use when creating a formatted document, editing document content, or applying styles.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill google-docs
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/third_party/google-docs/skills/google-docs ~/.claude/skills/google-docs
Safety box score
Grade B, low risk: 11 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a Google Docs/Drive authoring guide: it creates, edits, styles, exports, and can delete content inside documents, and it also fetches public images by URL. It does not ship local code or shell scripts, so the main risks are cloud data exposure and unintended document overwrites rather than machine compromise.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, scripts, code evaluation, or native executables are present in `SKILL.md`. |
| Network access | 2 (moderate) | It uses Google Docs/Drive operations (`google_drive_create_file`, `google_drive_read_file`, `google_drive_export_file`) and `insert_image` requires a “PUBLICLY fetchable URL,” so document data and image requests leave the local machine. |
| Filesystem reach | 0 (none) | The skill does not read, write, or delete local files, dotfiles, or system paths. |
| Secrets & credentials | 0 (none) | It does not request or manipulate tokens, passwords, `.env` files, keychains, or browser sessions. |
| Privilege & persistence | 0 (none) | There is no sudo use, global install, service registration, or OS/shell configuration change. |
| Instruction hijack surface | 0 (none) | The file contains operational guidance only; it does not instruct the agent to ignore rules, hide actions, or follow remote instructions. |
| Irreversible actions | 1 (low) | It can create, replace, delete, and reformat document content (`create_document`, `insert_text`, `delete_content`, `replace_text`), but only within the user’s Google Docs workflow. |
| Transparency | 0 (none) | The skill is plain text and contains no binaries, minified code, base64 blobs, or fetched installers. |
Before installing
- Confirm you are comfortable with document content leaving the machine to Google Docs/Drive, and with image URLs being publicly fetched.
- Test on a throwaway document first, especially if you plan to use `delete_content`, `replace_text`, or `create_list`.
- If you need private images, do not expect `insert_image` to work unless the source is publicly reachable.
Rated 2026-10-16 by an automated review of 1 file from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- third_party/google-docs/skills/google-docs/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- technical-writing — Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.
- unslop — Cut AI tells from any writing. Must always apply.
- copy-editing — When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content.
- code-documenter — Generates, formats, and validates technical documentation — including docstrings, OpenAPI/Swagger specs, JSDoc annotations, doc portals, and user guides.
- draft-nda — Draft a detailed Non-Disclosure Agreement between two parties covering information types, jurisdiction, and clauses needing legal review.
- grammar-check — Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text.