gmail-ai

AI-enhanced Gmail — smart email triage, priority scoring, AI-generated replies, thread summarization, and automated categorization. IMAP/SMTP with OpenRouter-powered intelligence. Use for inbox zero, email management, smart replies, and email automation.

3,891 stars

Best use case

gmail-ai is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

AI-enhanced Gmail — smart email triage, priority scoring, AI-generated replies, thread summarization, and automated categorization. IMAP/SMTP with OpenRouter-powered intelligence. Use for inbox zero, email management, smart replies, and email automation.

Teams using gmail-ai should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/gmail-ai/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aiwithabidi/gmail-ai/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/gmail-ai/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How gmail-ai Compares

Feature / Agentgmail-aiStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

AI-enhanced Gmail — smart email triage, priority scoring, AI-generated replies, thread summarization, and automated categorization. IMAP/SMTP with OpenRouter-powered intelligence. Use for inbox zero, email management, smart replies, and email automation.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 📧 Gmail AI

AI-enhanced Gmail for OpenClaw agents. Fork of gmail v1.0.6 with AI triage, priority scoring, smart replies, and email summarization.

## What's New vs gmail

- **AI triage** — auto-categorize emails (urgent/actionable/FYI/spam)
- **Priority scoring** — 0-100 score based on sender, subject, content
- **Smart replies** — context-aware reply generation in multiple tones
- **Email summarization** — TL;DR for long threads
- **Send email** — compose and send via SMTP

## Requirements

| Variable | Required | Description |
|----------|----------|-------------|
| `GMAIL_ADDRESS` | ✅ | Your Gmail address |
| `GMAIL_APP_PASSWORD` | ✅ | Gmail App Password ([create one](https://myaccount.google.com/apppasswords)) |
| `OPENROUTER_API_KEY` | Optional | For AI triage, replies, and summaries |

## Quick Start

```bash
# Fetch recent unread emails
python3 {baseDir}/scripts/gmail_ai.py inbox --unread --limit 10

# Fetch by label
python3 {baseDir}/scripts/gmail_ai.py inbox --label INBOX --limit 20

# Fetch from specific sender
python3 {baseDir}/scripts/gmail_ai.py inbox --from "boss@company.com"

# AI triage — categorize emails
python3 {baseDir}/scripts/gmail_ai.py triage --limit 20

# Priority scoring
python3 {baseDir}/scripts/gmail_ai.py priority --limit 20

# Summarize an email thread
python3 {baseDir}/scripts/gmail_ai.py summarize <message_id>

# Generate smart reply
python3 {baseDir}/scripts/gmail_ai.py reply <message_id> --tone professional
python3 {baseDir}/scripts/gmail_ai.py reply <message_id> --tone friendly
python3 {baseDir}/scripts/gmail_ai.py reply <message_id> --tone brief

# Send email
python3 {baseDir}/scripts/gmail_ai.py send --to "recipient@example.com" --subject "Hello" --body "Message body"

# Send with CC/BCC
python3 {baseDir}/scripts/gmail_ai.py send --to "a@b.com" --cc "c@d.com" --subject "Hello" --body "Message"
```

## Commands

### `inbox`
Fetch emails from Gmail via IMAP.
- `--unread` — only unread messages
- `--label LABEL` — Gmail label/folder (default: INBOX)
- `--from ADDRESS` — filter by sender
- `--limit N` — max results (default: 10)
- `--since YYYY-MM-DD` — emails since date

### `triage`
AI-powered email categorization (requires `OPENROUTER_API_KEY`).
- Categories: 🔴 Urgent, 🟡 Actionable, 🔵 FYI, ⚪ Spam/Noise
- `--limit N` — number of emails to triage

### `priority`
Score emails 0-100 based on sender importance, subject urgency, and content.
- `--limit N` — number of emails to score
- Factors: known sender, urgency keywords, mentions of you, deadlines

### `summarize <message_id>`
Generate a TL;DR summary of an email or thread.

### `reply <message_id>`
Generate a context-aware reply draft.
- `--tone professional|friendly|brief|formal` — reply style
- `--context TEXT` — additional context for the reply

### `send`
Send email via SMTP.
- `--to ADDRESS` — recipient (required)
- `--subject TEXT` — subject line (required)
- `--body TEXT` — email body (required)
- `--cc ADDRESS` — CC recipient
- `--bcc ADDRESS` — BCC recipient

## Security Notes

- Uses Gmail App Passwords (not OAuth) — simpler setup, works with 2FA
- App Password is NOT your Google password
- Create one at: Google Account → Security → 2-Step Verification → App Passwords
- IMAP must be enabled in Gmail settings

## Credits
Built by [M. Abidi](https://www.linkedin.com/in/mohammad-ali-abidi) | [agxntsix.ai](https://www.agxntsix.ai)
[YouTube](https://youtube.com/@aiwithabidi) | [GitHub](https://github.com/aiwithabidi)
Part of the **AgxntSix Skill Suite** for OpenClaw agents.

📅 **Need help setting up OpenClaw for your business?** [Book a free consultation](https://cal.com/agxntsix/abidi-openclaw)

Related Skills

Skill: Gmail Auto-Reply for Client

3891
from openclaw/skills

## Purpose

gmail-summarize

3891
from openclaw/skills

Fetch recent unread Gmail (yesterday + today) and send a digest to the user.

gmail-label-routing

3891
from openclaw/skills

Configurar en Gmail el enrutamiento por remitente hacia etiquetas usando el workflow local `scripts/gws_gmail_label_workflow.py`, incluyendo crear/usar etiqueta, crear filtro, aplicar retroactivo y opcionalmente sacar de INBOX. Usar cuando el usuario pida cosas como “manda este remitente a esta etiqueta”, “hazlo para varios remitentes”, “aplícalo a correos existentes”, “sácalos de INBOX”, o “limpia/reemplaza filtros duplicados para ese remitente”.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure