xresearch

xresearch — Twitter/X Profile Intelligence

---

Step 1: Parse & Setup

1. Extract the handle from $ARGUMENTS (strip @ if present, strip whitespace).
2. Create a slug from the handle (lowercase, as-is). Example: trading_wise → trading_wise.
3. Set paths:
   • PROSPECT_DIR = prospects/{slug}/
   • RAW_DATA = prospects/{slug}/twitter_raw_data.json
   • OUTPUT = prospects/{slug}/notes/xresearcher-intake.md
   • COOKIES = plugins/xresearch/.cookies.json
   • SCRAPER = plugins/xresearch/xresearch.py
4. Create directories: prospects/{slug}/notes/ (use mkdir -p).

IMPORTANT: Before running the scraper, check if twitter_raw_data.json already exists at the output path. Also check for legacy raw_data.json (older runs). If either exists, ask the user:

"twitter_raw_data.json (or raw_data.json) already exists for {handle}. Use existing data or re-scrape?" If they say use existing, skip Step 2 entirely. If using legacy raw_data.json, set RAW_DATA to that path.

---

Step 2: Run Scraper

Run the Playwright scraper via Bash:

cd /Users/ketankhairnar/Desktop/AIC && python plugins/xresearch/xresearch.py {handle} {RAW_DATA} --cookies {COOKIES}

• If exit code != 0, show the error and STOP. Do not proceed with stale or missing data.
• If successful, read twitter_raw_data.json and report:

✓ Scraper complete
  Tweets: {meta.tweet_count_collected} ({meta.date_range[0]} to {meta.date_range[1]})
  Following: {meta.following_collected}/{meta.following_total}
  Links: {links count} extracted, {scraped_links count} scraped
  Status: {scrape_status summary}

---

Step 3: Read Raw Data

Read the full twitter_raw_data.json into context. You need ALL of it for the analysis passes.

---