Browser Automation & Scraping Toolkit

What it does

Covers reliable browser automation (Playwright/Puppeteer/nodriver) for scraping or testing social platforms, including cookie/session persistence, stealth configuration, and proxy/CAPTCHA strategy. Only collects publicly available data and respects each platform's terms and rate limits.

When to use it

• You need to scrape public profile or content data for lead research or competitor analysis
• You're automating a repetitive browser task (login, form fill, data pull) across sessions
• You need platform-specific handling for Instagram, LinkedIn, X/Twitter, TikTok, or YouTube without tripping anti-bot defenses

Steps

1. Define the exact data needed and confirm it's publicly accessible and allowed to collect
2. Set up the automation framework with session/cookie persistence to avoid repeat logins
3. Apply stealth settings (patched automation signatures, realistic timing) appropriate to the platform
4. Add proxy rotation and CAPTCHA handling strategy if the target requires it
5. Run a small test batch first and verify output quality before scaling
6. Store collected data in the agreed destination (e.g. a CRM or sheet feeding GoHighLevel) without exposing credentials in logs or chat

The skill

---
name: browser-automation-scraping-toolkit
description: Automate browsers and scrape social platforms safely with session persistence, anti-detection, and per-platform playbooks.
---

# Browser Automation & Scraping Toolkit

## 1. Overview
Covers reliable browser automation (Playwright/Puppeteer/nodriver) for scraping or testing social platforms, including cookie/session persistence, stealth configuration, and proxy/CAPTCHA strategy. Only collects publicly available data and respects each platform's terms and rate limits.

## 2. When to Use
- You need to scrape public profile or content data for lead research or competitor analysis
- You're automating a repetitive browser task (login, form fill, data pull) across sessions
- You need platform-specific handling for Instagram, LinkedIn, X/Twitter, TikTok, or YouTube without tripping anti-bot defenses

## 3. Steps
1. Define the exact data needed and confirm it's publicly accessible and allowed to collect
2. Set up the automation framework with session/cookie persistence to avoid repeat logins
3. Apply stealth settings (patched automation signatures, realistic timing) appropriate to the platform
4. Add proxy rotation and CAPTCHA handling strategy if the target requires it
5. Run a small test batch first and verify output quality before scaling
6. Store collected data in the agreed destination (e.g. a CRM or sheet feeding GoHighLevel) without exposing credentials in logs or chat

## 4. GoHighLevel Angle
Apply this inside GoHighLevel workflows (funnels, automations, or client reporting) wherever the same task recurs for an agency or client account.

## 5. Safety Rules
- Always produce a draft first; never send, publish, or spend money without explicit human approval.
- Never invent data, metrics, or results — use only what is confirmed or clearly label estimates.
- Never paste API keys, tokens, or passwords into chat; reference secrets by name from a secure store.

For Claude Code, save it as ~/.claude/skills/browser-automation-scraping-toolkit/SKILL.md. In Cursor, ChatGPT or another assistant, paste it as project instructions.