Who it is forA part-time trader who cannot watch thousands of charts at the open but wants a shortlist with context.
The problemFinding setups by hand means flipping through charts and headlines while the move is already happening.
The outcomeA shortlist of stocks that broke their opening range, with the morning's headlines and filings for each.
What you need first
- Claude Code (or any Claude chat, without the Python tools)
- Python 3.8 or newer; nothing to pip install
- For SEC tools: your name and email in trader/config.json or SEC_USER_AGENT
- For orders only: a brokerage connector such as Alpaca's MCP server, paper account by default
Steps
- In Claude Code run
/plugin marketplace add Jakeschincariol/day-trader-skillthen/plugin install day-trader-skill@day-trader-skill - Or copy the folders:
cp -r day-trader-skill/trader-* ~/.claude/skills/after cloning - Run
/trader-scanner, or the tool directly:python3 trader-scanner/scan.py orb --at 10:15 - Run
/trader-newson the hits, for examplepython3 trader-news/news.py --tickers TSLA --hours 12 - Add your name and email as sec_user_agent in trader/config.json so the SEC tools work
Prompt for your agent
Install Jakeschincariol/day-trader-skill, run the opening-range breakout scan at <time ET>, then run the news monitor on the top <n> hits. Give me a table of ticker, range, breakout size and the main headline, and do not plan or place any trade.
Caveat. The scanner reads free Yahoo Finance 1 or 5 minute bars, which can lag or be rate limited. Not financial advice: paper trade first, and remember you can lose money.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Jakeschincariol/day-trader-skill and "Scan thousands of stocks for opening-range breakouts"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer