Airtable Automation logo

Airtable Automation

Organization
claude-office-skills
airtable-automation

Airtable database automation - views, automations, integrations, and workflow triggers

Overview

Publisherclaude-office-skills
Repositoryskills
Skill nameairtable-automation
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 Airtable Automation 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/airtable-automation
  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/airtable-automation .claude/skills/airtable-automation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Airtable Automation 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 Airtable Automation 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 Airtable Automation 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.

Airtable Automation

Automate Airtable bases with views, automations, integrations, and cross-platform workflows. Based on n8n's Airtable integration templates.

Overview

This skill covers:

  • Database design and views
  • Built-in automations
  • n8n integration workflows
  • Formula and rollup design
  • Reporting and dashboards

Database Design

Base Structure Template

yaml
base: "Project Management"

tables:
  Projects:
    fields:
      - Name: single_line_text (primary)
      - Status: single_select [Planning, Active, On Hold, Complete]
      - Priority: single_select [P0, P1, P2, P3]
      - Owner: collaborator
      - Start Date: date
      - Due Date: date
      - Budget: currency
      - Tasks: link_to_records (Tasks)
      - Progress: rollup (Tasks.Status, COUNTIF(Done)/COUNT)
      - Days Remaining: formula (DATETIME_DIFF(Due Date, TODAY(), 'days'))
      
  Tasks:
    fields:
      - Task Name: single_line_text (primary)
      - Project: link_to_records (Projects)
      - Status: single_select [To Do, In Progress, Review, Done]
      - Assignee: collaborator
      - Due Date: date
      - Hours Estimated: number
      - Hours Actual: number
      - Attachments: attachment
      
  Team:
    fields:
      - Name: single_line_text (primary)
      - Email: email
      - Role: single_select [PM, Developer, Designer, QA]
      - Current Projects: link_to_records (Projects)
      - Capacity: number (hours/week)
      - Utilization: rollup (calculate from Tasks)

Views Configuration

yaml
views:
  Projects:
    - Grid: All Projects
        fields: [Name, Status, Owner, Due Date, Progress]
        sort: Due Date (ascending)
        
    - Kanban: By Status
        group_by: Status
        card_fields: [Name, Owner, Due Date]
        
    - Calendar: Timeline
        date_field: Due Date
        
    - Gallery: Project Cards
        cover: Attachments
        
  Tasks:
    - Grid: My Tasks
        filter: Assignee = {Current User}
        sort: Due Date
        
    - Kanban: Sprint Board
        group_by: Status
        
    - Calendar: Task Calendar
        date_field: Due Date

Automations

Built-in Airtable Automations

yaml
automation_1:
  name: "New Task Notification"
  trigger:
    when: record_created
    table: Tasks
  actions:
    - send_slack:
        channel: "#project-updates"
        message: |
          📋 New task created!
          Task: {Task Name}
          Project: {Project}
          Assignee: {Assignee}
          Due: {Due Date}

automation_2:
  name: "Overdue Task Alert"
  trigger:
    when: record_matches_conditions
    table: Tasks
    conditions:
      - Status: not "Done"
      - Due Date: before today
  actions:
    - send_email:
        to: "{Assignee.email}"
        subject: "⚠️ Overdue Task: {Task Name}"
        body: "Your task '{Task Name}' was due on {Due Date}."
    - update_record:
        field: Status
        value: "Overdue"

automation_3:
  name: "Project Complete"
  trigger:
    when: record_updated
    table: Projects
    field: Progress
    condition: equals 100%
  actions:
    - update_record:
        field: Status
        value: "Complete"
    - send_slack:
        channel: "#wins"
        message: "🎉 Project '{Name}' completed!"

n8n Integration Workflows

yaml
workflow: "Form to Airtable to CRM"

trigger: typeform_submission

steps:
  1. create_airtable_record:
      base: "Leads"
      table: "Contacts"
      fields:
        Name: "{form.name}"
        Email: "{form.email}"
        Company: "{form.company}"
        Source: "Website Form"
        Created: "{timestamp}"
        
  2. enrich_data:
      clearbit: lookup_email
      update_record:
        Company Size: "{clearbit.company_size}"
        Industry: "{clearbit.industry}"
        
  3. sync_to_hubspot:
      create_contact:
        email: "{email}"
        properties: from_airtable
        
  4. notify_sales:
      slack:
        channel: "#new-leads"
        message: "New lead: {Name} from {Company}"

Formula Reference

Common Formulas

yaml
formulas:
  days_until_due:
    formula: "DATETIME_DIFF({Due Date}, TODAY(), 'days')"
    output: number
    
  is_overdue:
    formula: "IF(AND({Status}!='Done', {Due Date}<TODAY()), 'Yes', 'No')"
    output: text
    
  full_name:
    formula: "CONCATENATE({First Name}, ' ', {Last Name})"
    output: text
    
  progress_bar:
    formula: |
      REPT('▓', ROUND({Progress}/10, 0)) & 
      REPT('░', 10-ROUND({Progress}/10, 0)) & 
      ' ' & ROUND({Progress}, 0) & '%'
    output: text (visual progress)
    
  status_emoji:
    formula: |
      SWITCH({Status},
        'To Do', '⬜',
        'In Progress', '🔵',
        'Review', '🟡',
        'Done', '✅',
        '❓'
      )
    output: text
    
  workdays_remaining:
    formula: "WORKDAY_DIFF(TODAY(), {Due Date})"
    output: number
    
  quarter:
    formula: |
      'Q' & CEILING(MONTH({Date})/3) & ' ' & YEAR({Date})
    output: text

Rollup Examples

yaml
rollups:
  task_count:
    linked_field: Tasks
    aggregation: COUNT(values)
    
  total_hours:
    linked_field: Tasks
    rollup_field: Hours Estimated
    aggregation: SUM(values)
    
  completion_rate:
    linked_field: Tasks
    rollup_field: Status
    aggregation: |
      COUNTALL(IF(values='Done', 1)) / COUNT(values) * 100
      
  average_rating:
    linked_field: Reviews
    rollup_field: Rating
    aggregation: AVERAGE(values)

Integration Patterns

Airtable + Slack

yaml
slack_integration:
  new_record_notification:
    trigger: record_created
    action: post_to_channel
    template: |
      *New {Table} Record*
      {Field1}: {value1}
      {Field2}: {value2}
      <{record_url}|View in Airtable>
      
  daily_digest:
    schedule: "9am weekdays"
    query: records_due_today
    action: post_summary
    
  slash_command:
    command: /airtable-add
    action: create_record_from_slack

Airtable + Calendar

yaml
calendar_sync:
  airtable_to_google:
    trigger: record_with_date_created
    action: create_calendar_event
    mapping:
      title: "{Name}"
      start: "{Date}"
      description: "{Notes}"
      
  google_to_airtable:
    trigger: calendar_event_created
    action: create_airtable_record
    mapping:
      Name: "{event.title}"
      Date: "{event.start}"
      Type: "Meeting"

Airtable + Zapier/n8n

yaml
multi_step_workflow:
  name: "Lead Processing Pipeline"
  
  trigger:
    platform: airtable
    event: new_record
    table: Raw Leads
    
  steps:
    - enrich:
        service: clearbit
        input: email
        output: company_data
        
    - score:
        service: ai_scoring
        criteria: [company_size, industry, title]
        output: lead_score
        
    - route:
        condition: lead_score
        high: assign_to_sales
        medium: add_to_nurture
        low: mark_as_cold
        
    - update_airtable:
        table: Qualified Leads
        fields: [enriched_data, score, assignment]
        
    - notify:
        if: high_score
        slack: dm_sales_rep

Reporting Templates

Weekly Status Report

yaml
report_automation:
  schedule: "Friday 5pm"
  
  queries:
    completed_this_week:
      table: Tasks
      filter: 
        - Status: Done
        - Completed Date: this_week
        
    in_progress:
      table: Tasks
      filter:
        - Status: In Progress
        
    overdue:
      table: Tasks
      filter:
        - Status: not Done
        - Due Date: before today
        
  output:
    format: markdown
    destination: [slack, email]
    template: |
      # Weekly Status Report - {week}
      
      ## Completed ({completed_count})
      {completed_list}
      
      ## In Progress ({in_progress_count})
      {in_progress_list}
      
      ## Overdue ({overdue_count}) ⚠️
      {overdue_list}
      
      ## Metrics
      - Completion rate: {rate}%
      - On-time delivery: {on_time}%

Dashboard View

yaml
dashboard:
  name: "Project Dashboard"
  
  widgets:
    - summary_bar:
        metrics:
          - Total Projects: COUNT(Projects)
          - Active: COUNT(Status='Active')
          - At Risk: COUNT(Days Remaining < 7)
          
    - progress_chart:
        type: bar
        data: Projects grouped by Status
        
    - upcoming_deadlines:
        type: list
        query: Projects where Due Date in next 14 days
        sort: Due Date ascending
        limit: 10
        
    - team_utilization:
        type: horizontal_bar
        data: Team members by task count

Output Example

Request: "Design an Airtable base for content marketing"

Output:

markdown
# Content Marketing Base

## Tables

### 1. Content Calendar
| Field | Type | Purpose |
|-------|------|---------|
| Title | Text | Content title |
| Status | Select | Idea → Draft → Review → Published |
| Type | Select | Blog, Video, Social, Email |
| Author | Collaborator | Assigned writer |
| Publish Date | Date | Target publish date |
| Platform | Multi-select | Blog, LinkedIn, Twitter |
| Keywords | Multi-select | SEO keywords |
| Performance | Link | → Analytics |

### 2. Analytics
| Field | Type | Purpose |
|-------|------|---------|
| Content | Link | → Content Calendar |
| Views | Number | Page views |
| Engagement | Number | Likes + comments |
| Conversions | Number | CTAs clicked |
| Date | Date | Measurement date |

## Automations

**1. New Content Idea**

Trigger: Record created Action: Slack to #content-ideas


**2. Ready for Review**

Trigger: Status → Review Action: Email editor + set due date


**3. Published**

Trigger: Status → Published Action:

  • Post to social scheduler
  • Add analytics tracking row
  • Celebrate in Slack 🎉

## Views
- 📅 Calendar View (by Publish Date)
- 📊 Kanban (by Status)
- 👤 My Content (filtered by Author)
- 📈 Performance Dashboard

Airtable Automation Skill - Part of Claude Office Skills

Frequently asked questions

What does the Airtable Automation AI skill do?

Airtable database automation - views, automations, integrations, and workflow triggers

Why use Airtable Automation on TypingMind?

Because you install it once and use it with any model. Airtable Automation 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 Airtable Automation in TypingMind?

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

Which AI models can use Airtable Automation?

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 Airtable Automation?

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

Is the Airtable Automation 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 👇