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)

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:

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:

export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=/path/to/credentials.json

Service account

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

Pre-obtained token

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

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

Command Pattern

gws \x3Cservice> \x3Cresource> \x3Cmethod> [--params '{}'] [--json '{}'] [flags]

All responses are structured JSON. Use jq for extraction.

Global Flags

Discover commands

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

# 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": "[email protected]"}'

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

Gmail

# 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:[email protected] 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": "[email protected]"}, "action": {"addLabelIds": ["LABEL_ID"], "removeLabelIds": ["INBOX"]}}'

Calendar

# 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": "[email protected]"}]}'

# 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": "[email protected]"}]}'

Sheets

# 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

# 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\
"}}]}'

Chat

# List spaces
gws chat spaces list

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

Tasks

# 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)

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

# Get user details
gws admin users get --params '{"userKey": "[email protected]"}'

Workflow Patterns

Pipeline: Find → Process → Act

# 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:

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

Tips

• Use gws schema \x3Cmethod> 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