data-connector

Create and maintain Playwright-based data connectors for web platforms.

15|9|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/vana-com/data-connectors --skill data-connector-vana-com
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-connector
Source: https://github.com/vana-com/data-connectors/tree/main/.claude/skills/data-connector
Command: npx skills add https://github.com/vana-com/data-connectors --skill data-connector-vana-com

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Building data connectors for web platforms is repetitive and error-prone; teams need a repeatable, auditable way to export user data while keeping credentials on-device.

Core Features & Use Cases

  • Scaffold and maintain Playwright-based connectors for multiple platforms.
  • Define scopes (e.g., platform.profile, platform.posts) and validate outputs against schemas.
  • Use cases include onboarding new platforms, updating existing connectors, and rapid prototyping for data pipelines.

Quick Start

Ask me to create a new data connector for a platform and specify the scopes you want to export.

Frequently Asked Questions about data-connector

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a Playwright data connector to export user data from web platforms?

You build Playwright data connectors by scaffolding scripts that use a two-phase model: logging in via UI and then extracting data headlessly. This approach exports user data from platforms like LinkedIn or Spotify while keeping credentials on-device.

Can I use Playwright to extract data from platforms requiring on-device credentials?

Yes, Playwright data connectors keep credentials on-device by separating the workflow into a UI login phase followed by headless data extraction. This ensures user data is exported securely without storing sensitive login information remotely.

How do I define scopes and validate outputs when creating web automation data connectors?

When creating data connectors, you define specific scopes like platform.profile or platform.posts and validate extracted outputs against schemas. This ensures the exported data maintains structural integrity and matches expected metadata formats.

What is the two-phase model used for Playwright data extraction?

The two-phase Playwright data extraction model consists of an initial login via the platform's UI followed by headless data extraction. This workflow allows automated scripts to authenticate securely and then rapidly export user data in the background.

Does this approach work for rapid prototyping of data pipelines for new platforms?

Yes, this approach supports rapid prototyping for data pipelines by providing reusable script scaffolding and metadata generation. You can quickly onboard new platforms or update existing connectors to export user data into your pipelines.

What platforms are supported by these Playwright data connectors?

Playwright data connectors can be built for platforms like LinkedIn, ChatGPT, and Spotify. The skill provides the scaffolding and workflow orchestration needed to export user data from similar web platforms.