Tool.Google Workspace.1a73bb6e82d43d1e logo

Tool.Google Workspace.1a73bb6e82d43d1e

Organization
AI45Lab
tool.google_workspace.1a73bb6e82d43d1e

Manage Google Workspace via the `gws` CLI — Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, Tasks, Meet, Slides, Forms, Contacts, and every other Workspace API. Use when: (1) listing, uploading, downloading, or sharing files on Google Drive, (2) reading, sending, labeling, or filtering Gmail messages, (3) creating, updating, or querying Google Calendar events, (4) reading or writing Google Sheets data, (5) creating or editing Google Docs, (6) sending Google Chat messages, (7) managing Google Tasks, (8) any other Google Workspace operation. Wraps the official `gws` CLI which dynamically discovers all Workspace APIs. Outputs structured JSON suitable for agent pipelines.

Overview

PublisherAI45Lab
RepositoryOpenART
Skill nametool.google_workspace.1a73bb6e82d43d1e
Stars
251
Forks
28
Bundled files
2
LicenseAGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by AI45Lab on GitHub. Read the source before you install it.

Installation

Install the Tool.Google Workspace.1a73bb6e82d43d1e AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/AI45Lab/OpenART/tree/main/openart-tools/tool.google_workspace.1a73bb6e82d43d1e
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AI45Lab/OpenART.git /tmp/OpenART
mkdir -p .claude/skills
cp -r /tmp/OpenART/openart-tools/tool.google_workspace.1a73bb6e82d43d1e .claude/skills/tool.google_workspace.1a73bb6e82d43d1e
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tool.Google Workspace.1a73bb6e82d43d1e in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tool.Google Workspace.1a73bb6e82d43d1e on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tool.Google Workspace.1a73bb6e82d43d1e is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Use this skill when the OpenART registry selects tool.google_workspace.1a73bb6e82d43d1e for the current task.

Google Workspace Skill

Operate all Google Workspace services through the gws CLI from OpenClaw.

Prerequisites

  • Node.js 18+
  • A Google Cloud project with OAuth credentials
  • gws CLI installed: npm install -g @googleworkspace/cli

Authentication

First-time setup (machine with browser)

bash
gws auth setup        # creates GCP project, enables APIs, logs in
gws auth login -s drive,gmail,sheets,calendar   # pick services you need

Headless server (no browser)

Complete auth on a machine with a browser, then export:

bash
gws auth export --unmasked > credentials.json

Security notes:

  • Set file permissions: chmod 600 credentials.json
  • Do not commit credential files to git — add credentials.json to your .gitignore
  • For production environments, prefer using a service account instead of user credentials

On the headless server:

bash
export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=/path/to/credentials.json

Service account

bash
export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=/path/to/service-account.json

Pre-obtained token

bash
export GOOGLE_WORKSPACE_CLI_TOKEN=$(gcloud auth print-access-token)

Priority: Token env > Credentials file env > gws auth login store > plaintext file.

Command Pattern

bash
gws <service> <resource> <method> [--params '{}'] [--json '{}'] [flags]

All responses are structured JSON. Use jq for extraction.

Global Flags

FlagPurpose
--dry-runPreview request without executing
--page-allStream all pages as NDJSON
--fields 'a,b'Select response fields
--output tableTable output for humans

Discover commands

bash
gws --help              # list all services
gws drive --help        # list resources in a service
gws drive files --help  # list methods on a resource
gws schema drive.files.list  # full request/response schema

Common Operations

Drive

bash
# List recent files
gws drive files list --params '{"pageSize": 10}'

# Search files
gws drive files list --params '{"q": "name contains '\''report'\''", "pageSize": 20}'

# Upload a file
gws drive +upload ./report.pdf

# Download a file
gws drive files get --params '{"fileId": "FILE_ID", "alt": "media"}' > output.pdf

# Create a folder
gws drive files create --json '{"name": "Project", "mimeType": "application/vnd.google-apps.folder"}'

# Share a file
gws drive permissions create \
  --params '{"fileId": "FILE_ID"}' \
  --json '{"role": "reader", "type": "user", "emailAddress": "user@example.com"}'

# List all pages
gws drive files list --params '{"pageSize": 100}' --page-all | jq -r '.files[].name'

Gmail

bash
# List inbox messages
gws gmail users-messages list --params '{"userId": "me", "maxResults": 10}'

# Read a message
gws gmail users-messages get --params '{"userId": "me", "id": "MSG_ID"}'

# Send an email
gws gmail users-messages send \
  --params '{"userId": "me"}' \
  --json '{"raw": "BASE64_ENCODED_EMAIL"}'

# Search messages
gws gmail users-messages list --params '{"userId": "me", "q": "from:boss@company.com is:unread"}'

# List labels
gws gmail users-labels list --params '{"userId": "me"}'

# Create a filter
gws gmail users-settings-filters create \
  --params '{"userId": "me"}' \
  --json '{"criteria": {"from": "noreply@example.com"}, "action": {"addLabelIds": ["LABEL_ID"], "removeLabelIds": ["INBOX"]}}'

Calendar

bash
# List upcoming events
gws calendar events list --params '{"calendarId": "primary", "timeMin": "2026-01-01T00:00:00Z", "maxResults": 10, "orderBy": "startTime", "singleEvents": true}'

# Create an event
gws calendar events insert \
  --params '{"calendarId": "primary"}' \
  --json '{"summary": "Team Sync", "start": {"dateTime": "2026-03-07T10:00:00+08:00"}, "end": {"dateTime": "2026-03-07T11:00:00+08:00"}, "attendees": [{"email": "user@example.com"}]}'

# Delete an event
gws calendar events delete --params '{"calendarId": "primary", "eventId": "EVENT_ID"}'

# Find free/busy slots
gws calendar freebusy query \
  --json '{"timeMin": "2026-03-07T00:00:00Z", "timeMax": "2026-03-07T23:59:59Z", "items": [{"id": "user@example.com"}]}'

Sheets

bash
# Create a spreadsheet
gws sheets spreadsheets create --json '{"properties": {"title": "Q1 Budget"}}'

# Read cell values
gws sheets spreadsheets-values get --params '{"spreadsheetId": "SHEET_ID", "range": "Sheet1!A1:D10"}'

# Write values
gws sheets spreadsheets-values update \
  --params '{"spreadsheetId": "SHEET_ID", "range": "Sheet1!A1", "valueInputOption": "USER_ENTERED"}' \
  --json '{"values": [["Name", "Amount"], ["Rent", "2000"]]}'

# Append a row
gws sheets spreadsheets-values append \
  --params '{"spreadsheetId": "SHEET_ID", "range": "Sheet1!A1", "valueInputOption": "USER_ENTERED"}' \
  --json '{"values": [["New Item", "500"]]}'

Docs

bash
# Create a document
gws docs documents create --json '{"title": "Meeting Notes"}'

# Get document content
gws docs documents get --params '{"documentId": "DOC_ID"}'

# Insert text (batchUpdate)
gws docs documents batchUpdate \
  --params '{"documentId": "DOC_ID"}' \
  --json '{"requests": [{"insertText": {"location": {"index": 1}, "text": "Hello World\n"}}]}'

Chat

bash
# List spaces
gws chat spaces list

# Send a message
gws chat spaces messages create \
  --params '{"parent": "spaces/SPACE_ID"}' \
  --json '{"text": "Deploy complete ✅"}'

Tasks

bash
# List task lists
gws tasks tasklists list

# List tasks
gws tasks tasks list --params '{"tasklist": "TASKLIST_ID"}'

# Create a task
gws tasks tasks insert \
  --params '{"tasklist": "TASKLIST_ID"}' \
  --json '{"title": "Review PR", "due": "2026-03-10T00:00:00Z"}'

Admin (Directory)

bash
# List users
gws admin users list --params '{"domain": "example.com"}'

# Get user details
gws admin users get --params '{"userKey": "user@example.com"}'

Workflow Patterns

Pipeline: Find → Process → Act

bash
# Find unread emails from boss, extract subjects
gws gmail users-messages list --params '{"userId": "me", "q": "from:boss is:unread"}' \
  | jq -r '.messages[].id' \
  | while read id; do
      gws gmail users-messages get --params "{\"userId\": \"me\", \"id\": \"$id\"}" \
        | jq -r '.payload.headers[] | select(.name=="Subject") | .value'
    done

Dry-run first

Always use --dry-run before destructive operations:

bash
gws drive files delete --params '{"fileId": "FILE_ID"}' --dry-run

Tips

  • Use gws schema <method> to discover exact parameter names and types.
  • All commands accept --params for URL/query parameters and --json for request body.
  • Pipe through jq for field extraction in agent pipelines.
  • Use --page-all for full result sets with automatic pagination.
  • Credentials are encrypted at rest (AES-256-GCM) with OS keyring.

Recipes

For 50+ ready-made workflow recipes (label & archive emails, organize Drive folders, schedule meetings, etc.), see the official recipe library.

Disclaimer

The gws CLI is not an officially supported Google product. It is a community/experimental tool. Use at your own discretion, and refer to the upstream repository for license and support details.

Troubleshooting

IssueFix
gws: command not foundnpm install -g @googleworkspace/cli
Auth fails / scope errorgws auth login -s drive,gmail (pick specific services)
"Access blocked" on loginAdd yourself as test user in GCP OAuth consent screen
Headless serverExport creds from a desktop, set GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE
Rate limitedAdd delays between calls, reduce pageSize

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Tool.Google Workspace.1a73bb6e82d43d1e AI skill do?

Manage Google Workspace via the `gws` CLI — Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, Tasks, Meet, Slides, Forms, Contacts, and every other Workspace API. Use when: (1) listing, uploading, downloading, or sharing files on Google Drive, (2) reading, sending, labeling, or filtering Gmail messages, (3) creating, updating, or querying Google Calendar events, (4) reading or writing Google Sheets data, (5) creating or editing Google Docs, (6) sending Google Chat messages, (7) managing Google Tasks, (8) any other Google Workspace operation. Wraps the official `gws` CLI which dynamically d...

Why use Tool.Google Workspace.1a73bb6e82d43d1e on TypingMind?

Because you install it once and use it with any model. Tool.Google Workspace.1a73bb6e82d43d1e is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tool.Google Workspace.1a73bb6e82d43d1e in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AI45Lab/OpenART/tree/main/openart-tools/tool.google_workspace.1a73bb6e82d43d1e. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tool.Google Workspace.1a73bb6e82d43d1e?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tool.Google Workspace.1a73bb6e82d43d1e?

As many as you like. As long as a model supports skills, you can use Tool.Google Workspace.1a73bb6e82d43d1e with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tool.Google Workspace.1a73bb6e82d43d1e AI skill free?

Yes. It is published on GitHub by AI45Lab under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇