What I Scheduled: Two scripts, two times, every trading day — no input from me. morning_prep.py runs at 8:00am. It scans for pre-market gappers, pulls the fundamentals, filters out ETFs, and emails me a game plan before the open. gapper_tracker.py runs at 4:30pm. It collects end-of-day data — gap %, volume, how it traded, next-day follow-through — and syncs everything to a Google Sheet automatically. Both run through Windows Task Scheduler. Scheduled Task or Loop? Scheduled task. The market runs on a fixed clock, so the automation does too. 8am before the open, 4:30pm after the close. One Surprise: The agent caught a bug I hadn't noticed. My gap % column was showing near-zero on stocks Finviz had flagged at 10%+. It traced the root cause to Polygon's adjusted=true flag inflating previous close on reverse-split stocks — silently corrupting my historical data. Two-line fix. But I wasn't looking for it. The agent found it on its own while doing something else. That's the part that stuck with me — it catches things you weren't watching for.

Just got my first business website live — gethotlineai.com Built it with Claude Code over the last few days. Zero prior web dev experience. The site is for Hotline AI — an AI speed-to-lead service for car dealerships that responds to internet leads in under 60 seconds. Biggest hack: Having Claude screenshot the site, compare it to a reference, and iterate until it matched — no guessing, no back and forth with myself. Just: screenshot → diff → fix → repeat. What surprised me most: The hardest part wasn't the code. It was the DNS. Spent more time fighting Namecheap and Vercel than I did building the actual site. But that's the real education — you don't know what you don't know until something breaks. Site is live, form submissions go to my business email, custom domain is connected. Onto the next.

Hey guys, I just want to drop in here to share some screenshots of the first newsletter that I built. I designed the style and the fonts based on what I really like to read and what was eye-catching for me. The charts, unfortunately, I wasn't able to get access to my Gemini image creator so I end up using matplotlib. However that's only going to create that same chart that you see on the screenshot. Eventually once I fix my Gemini image creation tool, really just fix my billing, I should be good to go. The newsletter would have generating images and it would be much more functional. Anyways I just want to drop this for my day 1 challenge. I appreciate anyone that stops and takes a look at it and if you have any comments or anything you want to add of value, I would definitely appreciate that as well. Best of luck, keep building, and let's get this money people!

I am super delayed on this post. I'm making this today because I finally got my skill library together and now I'm ready to move on to day four but before I do I want to share a couple of things with the community and show you what I created. Skill 1: /morning-prep Pulls pre-market gappers (≥10% gap, price >$1) from Finviz Elite every morning at 8 AM before the market opens. Enriches each ticker with float, short float %, ATR(14), and relative volume — all from Finviz, no yfinance. Checks SEC EDGAR for dilution filings in the last 30 days (S-3, S-1, 424B). Grabs the top 3 news headlines per ticker. Then sends me a ranked HTML leaderboard email with two sections: - Priority Watchlist — long setups scored on catalyst, gap %, RVOL, and ATR - Short Watch — dilution tickers flagged in red, sorted by gap size (biggest gap = best short candidate) I type /morning-prep and it either sets up the scheduler or fires it on demand. Runs every weekday automatically via Windows Task Scheduler, wakes the machine if needed. Skill 2: /gapper-tracker This one's building a statistical database to prove or disprove the Day 2 short edge — the idea that 67.7%(small sample)*not investment advice* of gap-up stocks close lower on Day 2 than Day 1. Every afternoon at 4:30 PM it logs intraday data from that day's gappers into a CSV with 30+ columns: open, high, low, close, gap fill %, range %, time of HOD, catalyst, pre-market VWAP, the works. The tricky part was multi-day staging. A ticker that gapped today needs Day 2 close filled tomorrow, and Day 3 close the day after — without creating duplicate rows. Built a JSON staging file to track which tickers are waiting on which day's data. When D3 is filled it writes the final row and removes it from staging. One optimization I made: On the morning-prep script, I was originally making individual API calls per ticker to pull enrichment data. Watched the agent work and saw it hitting rate limits constantly. Switched to Finviz batch calls — two requests cover all 15 tickers at once (one for ownership data, one for technicals). Went from 15+ calls and timeouts to 2 clean calls. That one change made the whole thing reliable.

Hey everyone, I'm on day three trying to build my skills but I'm looking for the skills builder boulder and I can't seem to find it. Does anyone know where it's at or has anyone had any trouble with this as well? Looks like at the time Nate recorded his video, versus now, he has changed things up a little bit so just need some help navigating.