Gmail Workflows logo

Gmail Workflows

Organization
claude-office-skills
gmail-workflows

Automate Gmail with intelligent workflows - attachment management, email organization, auto-archiving, and Google Drive integration

Overview

Publisherclaude-office-skills
Repositoryskills
Skill namegmail-workflows
Stars
514
Forks
97
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by claude-office-skills on GitHub. Read the source before you install it.

Installation

Install the Gmail Workflows 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/claude-office-skills/skills/tree/main/gmail-workflows
  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/claude-office-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/gmail-workflows .claude/skills/gmail-workflows
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gmail Workflows 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 Gmail Workflows 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 Gmail Workflows 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.

Gmail Workflows

Automate Gmail with intelligent workflows for attachment management, email organization, and Google Drive integration. Based on n8n's 7,800+ workflow templates.

Overview

This skill helps you design and implement Gmail automation workflows that:

  • Automatically save attachments to Google Drive
  • Organize emails with smart labeling
  • Archive processed emails
  • Send notifications via Slack/Email
  • Track email metrics

Core Workflow Templates

1. Gmail Attachment Manager

Purpose: Automatically extract attachments from emails and save to Google Drive

Workflow Steps:

┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│ Gmail       │───▶│ Filter by   │───▶│ Extract     │───▶│ Upload to   │
│ Trigger     │    │ Criteria    │    │ Attachments │    │ Google Drive│
└─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘
                                                                │
                         ┌─────────────┐    ┌─────────────┐    │
                         │ Send        │◀───│ Apply Label │◀───┘
                         │ Notification│    │ & Archive   │
                         └─────────────┘    └─────────────┘

Configuration:

yaml
trigger:
  type: gmail_new_email
  filters:
    has_attachment: true
    from: ["*@company.com", "*@vendor.com"]
    subject_contains: ["invoice", "report", "contract"]

actions:
  - extract_attachments:
      file_types: [pdf, xlsx, docx, csv]
      max_size_mb: 25
  
  - upload_to_drive:
      folder_path: "/Attachments/{year}/{month}"
      naming_pattern: "{filename}_{sender}_{date}"
      create_folder_if_missing: true
  
  - organize_email:
      apply_label: "Processed/Attachments"
      mark_as_read: true
      archive: true
  
  - notify:
      channel: slack
      message: "New attachment saved: {filename} from {sender}"

Best Practices:

  • Use specific sender filters to avoid processing spam
  • Set file size limits to prevent storage issues
  • Use date-based folder structure for easy retrieval
  • Enable duplicate detection to avoid redundant uploads

2. Invoice Auto-Archiver

Purpose: Automatically collect and organize invoices from email

Workflow Steps:

Gmail Trigger → Detect Invoice → Extract PDF → OCR/Parse → Save to Drive → Update Spreadsheet → Archive Email

Configuration:

yaml
trigger:
  subject_patterns:
    - "invoice"
    - "bill"
    - "statement"
    - "付款"
    - "发票"

processing:
  - detect_invoice:
      methods: [subject_keywords, attachment_name, sender_domain]
  
  - extract_data:
      fields: [invoice_number, amount, date, vendor, due_date]
      use_ocr: true
  
  - save_to_drive:
      folder: "/Finance/Invoices/{year}/{vendor}"
      naming: "{date}_{vendor}_{amount}"
  
  - update_tracker:
      spreadsheet: "Invoice Tracker"
      columns: [Date, Vendor, Amount, Invoice#, Status, File_Link]
  
  - archive:
      label: "Finance/Invoices"
      star: true

3. Client Communication Organizer

Purpose: Automatically organize client emails by project/client

Configuration:

yaml
rules:
  - name: "Client A Emails"
    condition:
      from_domain: "clienta.com"
    actions:
      - apply_label: "Clients/Client A"
      - forward_to: "team-a@company.com"
      - save_attachments: "/Clients/Client A/{subject}"

  - name: "Project X Updates"
    condition:
      subject_contains: ["Project X", "PX-"]
    actions:
      - apply_label: "Projects/Project X"
      - add_to_task: "Project X Board"
      - notify_slack: "#project-x"

  - name: "Urgent Requests"
    condition:
      subject_contains: ["URGENT", "ASAP", "紧急"]
      is_unread: true
    actions:
      - apply_label: "Priority/Urgent"
      - send_sms: "+1234567890"
      - move_to_inbox: true

4. Email Analytics Dashboard

Purpose: Track email metrics and generate reports

Metrics to Track:

yaml
daily_metrics:
  - emails_received: count(inbox)
  - emails_sent: count(sent)
  - response_time_avg: avg(reply_time)
  - unread_count: count(unread)
  - attachment_count: count(has_attachment)

weekly_report:
  - top_senders: group_by(from, count)
  - busiest_hours: group_by(hour, count)
  - label_distribution: group_by(label, count)
  - response_rate: sent / received

automation:
  - schedule: "every Monday 9am"
  - output: Google Sheets
  - notify: Slack #email-metrics

Implementation Guide

Using n8n

javascript
// n8n Workflow: Gmail to Google Drive
{
  "nodes": [
    {
      "name": "Gmail Trigger",
      "type": "n8n-nodes-base.gmailTrigger",
      "parameters": {
        "pollTimes": { "item": [{ "mode": "everyMinute" }] },
        "filters": { "labelIds": ["INBOX"] }
      }
    },
    {
      "name": "Filter Attachments",
      "type": "n8n-nodes-base.if",
      "parameters": {
        "conditions": {
          "boolean": [{
            "value1": "={{ $json.hasAttachment }}",
            "value2": true
          }]
        }
      }
    },
    {
      "name": "Get Attachments",
      "type": "n8n-nodes-base.gmail",
      "parameters": {
        "operation": "getAttachments",
        "messageId": "={{ $json.id }}"
      }
    },
    {
      "name": "Upload to Drive",
      "type": "n8n-nodes-base.googleDrive",
      "parameters": {
        "operation": "upload",
        "folderId": "your-folder-id",
        "name": "={{ $json.filename }}"
      }
    }
  ]
}

Using Google Apps Script

javascript
// Gmail to Drive Automation
function processNewEmails() {
  const threads = GmailApp.search('has:attachment is:unread');
  const targetFolder = DriveApp.getFolderById('FOLDER_ID');
  
  threads.forEach(thread => {
    const messages = thread.getMessages();
    messages.forEach(message => {
      const attachments = message.getAttachments();
      attachments.forEach(attachment => {
        // Save to Drive
        const file = targetFolder.createFile(attachment);
        
        // Rename with date and sender
        const newName = `${Utilities.formatDate(message.getDate(), 'GMT', 'yyyy-MM-dd')}_${message.getFrom()}_${attachment.getName()}`;
        file.setName(newName);
      });
      
      // Mark as processed
      message.markRead();
      thread.addLabel(GmailApp.getUserLabelByName('Processed'));
    });
  });
}

// Set up trigger
function setupTrigger() {
  ScriptApp.newTrigger('processNewEmails')
    .timeBased()
    .everyMinutes(5)
    .create();
}

Common Workflow Patterns

Pattern 1: Filter → Process → Organize → Notify

Email arrives
    │
    ▼
┌─────────────────┐
│ Apply Filters   │ → Skip if doesn't match
│ (sender, subject│
│  attachment)    │
└────────┬────────┘
         │
         ▼
┌─────────────────┐
│ Process Content │ → Extract data, attachments
│                 │
└────────┬────────┘
         │
         ▼
┌─────────────────┐
│ Organize        │ → Save files, apply labels
│                 │
└────────┬────────┘
         │
         ▼
┌─────────────────┐
│ Notify          │ → Slack, email, SMS
│                 │
└─────────────────┘

Pattern 2: Batch Processing

yaml
schedule: "daily at 6am"
steps:
  1. Collect all unprocessed emails from last 24h
  2. Group by category (invoices, reports, misc)
  3. Batch upload to respective Drive folders
  4. Generate summary report
  5. Send daily digest to stakeholders

Pattern 3: Conditional Routing

yaml
conditions:
  - if: attachment_type == "pdf" AND subject contains "invoice"
    then: route_to_finance_folder
  
  - if: from_domain in ["important-client.com"]
    then: priority_handling + immediate_notification
  
  - if: attachment_size > 10MB
    then: save_to_large_files_folder + skip_backup
  
  - default:
    then: standard_processing

Troubleshooting

Common Issues

IssueSolution
Attachments not detectedCheck MIME type filters, increase trigger frequency
Duplicate filesEnable deduplication by hash or filename
Rate limitsReduce trigger frequency, use batch processing
Permission errorsRe-authorize OAuth credentials
Large files failingSet size limits, use chunked upload

Security Considerations

  1. OAuth Scopes: Request minimal permissions

    • gmail.readonly for reading
    • gmail.modify for labels/archive
    • drive.file for Drive access
  2. Data Privacy:

    • Don't log email content
    • Use secure storage for credentials
    • Implement retention policies
  3. Access Control:

    • Limit who can modify workflows
    • Audit automation activities
    • Use separate service accounts

Output Example

Daily Email Report:

markdown
# Email Activity Report - 2026-01-30

## Summary
- Emails Received: 47
- Emails Sent: 23
- Attachments Processed: 12
- Average Response Time: 2.3 hours

## Attachment Processing
| File | Sender | Saved To | Time |
|------|--------|----------|------|
| Invoice_Jan.pdf | vendor@co.com | /Finance/Invoices | 09:15 |
| Report_Q4.xlsx | team@company.com | /Reports/Q4 | 10:30 |
| Contract_v2.docx | legal@client.com | /Contracts | 14:22 |

## Labels Applied
- Finance/Invoices: 5 emails
- Projects/Active: 12 emails
- Clients/Priority: 8 emails

## Pending Actions
- 3 emails require manual review
- 2 large attachments need approval

Gmail Workflows Skill - Part of Claude Office Skills

Frequently asked questions

What does the Gmail Workflows AI skill do?

Automate Gmail with intelligent workflows - attachment management, email organization, auto-archiving, and Google Drive integration

Why use Gmail Workflows on TypingMind?

Because you install it once and use it with any model. Gmail Workflows 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 Gmail Workflows in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/claude-office-skills/skills/tree/main/gmail-workflows. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gmail Workflows?

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 Gmail Workflows?

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

Is the Gmail Workflows AI skill free?

Yes. It is published on GitHub by claude-office-skills under the MIT 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 👇