agentleFS
OpenLaborOpenLabor/openlabor/skills/airtable-manager/SKILL.md

Airtable Manager

Skill5 starsChanged 3 months agoMITView on GitHub

Create, read, update, and delete records in Airtable bases — manage data, CRM, and project tracking via Composio

  • Reads credentials

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create, read, update, and delete records in Airtable — manage data, CRM, and project tracking.

    line 17
  2. Distinctive:

    Update deal stages as they progress

    line 113
  3. Distinctive:

    Add notes via comments on records

    line 114
  4. Distinctive:

    Create records for each piece of content

    line 117
  5. Distinctive:

    Add comments for updates

    line 125
  6. Very specific:

    Use AIRTABLE_CREATE_RECORDS (not the deprecated singular versions)

    line 130
  7. Distinctive:

    Always get the base schema first to understand available tables and fields

    line 131
  8. Distinctive:

    If you get a 400 "not connected" error, tell the user to connect Airtable in the Apps tab

    line 132

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- openlabor-connector: airtable, api_key={{INTERNAL_API_KEY}}, employee={{EMPLOYEE_ID}}, base={{API_BASE_URL}} -->

Airtable Manager

Create, read, update, and delete records in Airtable — manage data, CRM, and project tracking.

You have access to Airtable through the OpenLabor connector API.

How to Execute Airtable Actions

use airtable <TOOL_NAME> '<json_args>'

Getting Started

List All Bases

  • Tool: AIRTABLE_LIST_BASES
  • Args: {}

Get Base Schema

  • Tool: AIRTABLE_GET_BASE_SCHEMA
  • Args: { "baseId": "appXXXXXXXXXXXXXX" }

Get User Info

  • Tool: AIRTABLE_GET_USER_INFO
  • Args: {}

Records

List Records

  • Tool: AIRTABLE_LIST_RECORDS
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table Name", "pageSize": "100" }
  • Optional: "filterByFormula", "sort", "fields", "view", "maxRecords"
  • Filter example: "filterByFormula": "{Status} = 'Active'"
  • Sort example: "sort": [{"field": "Created", "direction": "desc"}]

Get Single Record

  • Tool: AIRTABLE_GET_RECORD
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table Name", "recordId": "recXXX" }

Create Records (up to 10)

  • Tool: AIRTABLE_CREATE_RECORDS
  • Args:
{
  "baseId": "appXXX",
  "tableIdOrName": "Table Name",
  "records": [
    { "fields": { "Name": "John", "Email": "john@example.com", "Status": "New" } }
  ]
}

Create Record from Natural Language

  • Tool: AIRTABLE_CREATE_RECORD_FROM_NATURAL_LANGUAGE
  • Args: { "baseId": "appXXX", "tableIdOrName": "Contacts", "nl_query": "Add John Smith, email john@smith.com, status is new lead" }

Update Records

  • Tool: AIRTABLE_UPDATE_RECORD
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table Name", "recordId": "recXXX", "fields": { "Status": "Contacted" } }
  • PATCH update — only modifies specified fields

Update Multiple Records

  • Tool: AIRTABLE_UPDATE_MULTIPLE_RECORDS
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table Name", "records": [{ "id": "recXXX", "fields": { "Status": "Done" } }] }

Delete Record

  • Tool: AIRTABLE_DELETE_RECORD
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table Name", "recordId": "recXXX" }

Delete Multiple Records

  • Tool: AIRTABLE_DELETE_MULTIPLE_RECORDS
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table Name", "recordIds": ["recXXX", "recYYY"] }

Tables & Fields

Create Table

  • Tool: AIRTABLE_CREATE_TABLE
  • Args: { "baseId": "appXXX", "name": "Leads", "fields": [{ "name": "Name", "type": "singleLineText" }, { "name": "Email", "type": "email" }] }

Create Field

  • Tool: AIRTABLE_CREATE_FIELD
  • Args: { "baseId": "appXXX", "tableIdOrName": "Leads", "name": "Score", "type": "number" }

Comments

Add Comment

  • Tool: AIRTABLE_CREATE_COMMENT
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table", "recordId": "recXXX", "text": "Following up on this" }

List Comments

  • Tool: AIRTABLE_LIST_COMMENTS
  • Args: { "baseId": "appXXX", "tableIdOrName": "Table", "recordId": "recXXX" }

Use Cases

As a CRM

  • Track leads, contacts, deals in Airtable tables
  • Filter by status: "filterByFormula": "{Stage} = 'Qualified'"
  • Update deal stages as they progress
  • Add notes via comments on records

As a Content Calendar

  • Create records for each piece of content
  • Track status (Draft → Review → Published)
  • Filter by date and platform
  • Link to published posts

As a Project Tracker

  • List tasks by assignee or status
  • Update completion status
  • Add comments for updates

Guidelines

  1. Rate limit: 5 requests/second per base
  2. Max 10 records per create/update/delete batch
  3. Use AIRTABLE_CREATE_RECORDS (not the deprecated singular versions)
  4. Always get the base schema first to understand available tables and fields
  5. If you get a 400 "not connected" error, tell the user to connect Airtable in the Apps tab

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.