facebook-group-monitorlisted

# Facebook Group Monitor Skill ## Overview Playwright-based headless browser scraper for Facebook groups. Default behavior: **captures a stitched "feed strip"** (scrolls 3× viewport, crops to feed column, stitches into 1 JPEG) → agent calls vision model once with a custom prompt to extract and interpret all new posts in a single LLM call. Requires one-time manual login via terminal to establish a persistent browser session. ## Setup See [references/SETUP.md](references/SETUP.md) for installation and first-time login instructions. ## File Locations (after install) - **Script**: `scripts/fb-group-monitor.py` - **Shell wrapper**: `scripts/fb-group-monitor.sh` - **Browser session**: auto-created at `scripts/.browser-data/` (persistent login) - **Seen posts**: auto-created at `scripts/.seen-posts.json` (dedup tracking) - **Screenshots**: `scripts/screenshots/` or custom `--shots-dir` ## Commands ### 1. Check login session ```bash scripts/fb-group-monitor.sh status ``` Output: ```json {"success": true, "action": "status", "message": "Session active — logged in to Facebook."} ``` ### 2. Scrape new posts (with feed strip screenshot) ```bash scripts/fb-group-monitor.sh scrape <GROUP_URL> [--limit N] [--shots-dir <PATH>] ``` **Parameters:** - `GROUP_URL`: Full URL (https://www.facebook.com/groups/123456) or just group ID - `--limit N`: Max posts to scrape (default: 10) - `--shots-dir <PATH>`: ⚠️ **REQUIRED for vision** — save screenshots in agent workspace so image tool can