skills/gmail/SKILL.md
Gmail automation via Google Apps Script. Use for: send emails, read inbox, create drafts, search messages.
npx skillsauth add aviz85/claude-skills-library gmailInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
First time? If
setup_complete: falseabove, run./SETUP.mdfirst, then setsetup_complete: true.
Full Gmail automation via Google Apps Script API: send, read inbox, create drafts, mark as read.
| Action | Description | Required Params | Optional |
|--------|-------------|-----------------|----------|
| send | Send email | to, subject, body | html, cc, bcc, name |
| inbox | Read inbox | - | maxResults, query, hours |
| draft | Create draft | to, subject, body | html, replyTo |
| markRead | Mark as read | messageId | - |
# Send email
curl -sL "$URL?token=$TOKEN&action=send&[email protected]&subject=Hello&body=Message"
# Get last 10 unread emails from last 6 hours
curl -sL "$URL?token=$TOKEN&action=inbox&maxResults=10&hours=6"
# Search for specific emails
curl -sL "$URL?token=$TOKEN&action=inbox&query=from:[email protected]"
# Create draft
curl -sL "$URL?token=$TOKEN&action=draft&[email protected]&subject=Follow%20Up&body=Draft"
# Mark email as read
curl -sL "$URL?token=$TOKEN&action=markRead&messageId=MESSAGE_ID"
Send:
{
"success": true,
"email": { "to": "[email protected]", "subject": "Hello", "cc": null, "bcc": null }
}
Inbox:
{
"success": true,
"count": 5,
"emails": [
{
"id": "message_id",
"threadId": "thread_id",
"from": "[email protected]",
"subject": "Email Subject",
"date": "2026-01-14T08:30:00Z",
"snippet": "First 200 chars...",
"body": "Full email body",
"isUnread": true,
"labels": ["INBOX", "UNREAD"]
}
]
}
is:unread with time filterhours param defaults to 24Works with other skills:
development
The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.
development
The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.
development
Search across all Claude Code conversation history (JSONL files) across all projects.
development
Deep code audit that detects misleading patterns — fake tests, mock abuse, shallow health checks, overly optimistic error handling, hidden debt. Produces a structured report with findings AND actionable recommendations. Use when code looks green but smells wrong.