A set of 11 Claude skills with Python tools that copy 13F-disclosed investor portfolios, monitor news and congressional trades, and size orders, requiring your approval before any trade.
Jakeschincariol/day-trader-skill
A set of 11 Claude skills with Python tools for day trading: chart scanning, news tracking, entry and exit timing, and backtest-style replays before risking money.
- Stars
- 5,931
- Forks
- 1,468
- Open issues
- 55
- Last commit
- 18 days ago
Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.
What is it?
This repository packages eleven Claude skills for day trading, each backed by a small standard-library Python tool. They scan thousands of charts for setups such as opening-range breakouts, track news on watched stocks, time entries bar by bar, and set stops and targets before a trade. The tools read free public data from Yahoo Finance, Nasdaq Trader, SEC EDGAR and the House Clerk, and require no API key.
The central feature is the Time Machine, which replays the rest of a session 10,000 times using the stock's recent 5-minute bars, and also re-runs the same rule on past sessions where the setup fired. Position sizing, risk checks and an order executor sit downstream, and the order executor only sends orders after the user confirms each one. Paper trading is the default.
The project is Python with an offline unittest suite built on recorded fixtures. Skills can be installed as a Claude Code plugin or copied into the skills folder.
Key features
- 01Scans a large stock universe for intraday setups such as opening-range breakouts.
- 02Tracks news and SEC filings for the stocks you watch.
- 03Times entries bar by bar and sets stop and target levels before entering.
- 04Replays possible trade outcomes 10,000 times using recent 5-minute bars.
- 05Sizes positions to a set max loss per trade and checks orders against risk limits.
- 06Requires explicit confirmation before any order is sent; paper trading is the default.
Use cases
- Testing a day-trading rule against a stock's recent history before trading it with real money.
- Getting a pre-market list of stocks with intraday setups.
- Planning stop and target levels for a trade before entering it.
- Monitoring news and earnings disclosures for a watchlist during the trading day.
Quick start
- 1
Clone the repository
git clone https://github.com/Jakeschincariol/day-trader-skill.git - 2
Copy the skill folders into your Claude skills directory
cp -r day-trader-skill/trader-* ~/.claude/skills/ - 3
Run the scanner to list the US stock universe
python3 trader-scanner/scan.py universe
Things to know
- The data comes from Yahoo Finance's unofficial chart endpoint, which can lag, change or rate-limit you.
- The SEC tools require your name and email in config or the SEC_USER_AGENT environment variable.
- The README warns that most people who day trade lose money, and it is not financial advice.
- Using the skills in Claude depends on Claude, and order placement depends on Alpaca's MCP server connector.
In collections
Topics
FAQ
- What is day-trader-skill?
- A set of 11 Claude skills with Python tools for day trading: chart scanning, news tracking, entry and exit timing, and backtest-style replays before risking money. This repository packages eleven Claude skills for day trading, each backed by a small standard-library Python tool. They scan thousands of charts for setups such as opening-range breakouts, track news on watched stocks, time entries bar by bar, and set stops and targets before a trade. The tools read free public data from Yahoo Finance, Nasdaq Trader, SEC EDGAR and the House Clerk, and require no API key.
- Is day-trader-skill free to use? What license does it have?
- day-trader-skill is open source under the MIT license. Check the license terms before using it in commercial products.
- Is day-trader-skill still maintained?
- Actively maintained. The last commit to day-trader-skill was on Oct 20, 2026.
- What can I use day-trader-skill for?
- Testing a day-trading rule against a stock's recent history before trading it with real money. Getting a pre-market list of stocks with intraday setups. Planning stop and target levels for a trade before entering it. Monitoring news and earnings disclosures for a watchlist during the trading day.
- How do I install day-trader-skill?
- Clone the repository: git clone https://github.com/Jakeschincariol/day-trader-skill.git Copy the skill folders into your Claude skills directory: cp -r day-trader-skill/trader-* ~/.claude/skills/ Run the scanner to list the US stock universe: python3 trader-scanner/scan.py universe
- Where can I get day-trader-skill?
- The source code and installation instructions are on GitHub: https://github.com/Jakeschincariol/day-trader-skill
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A local MCP server that gives AI assistants stock quotes, technical analysis, portfolio tracking and optional Python backtesting via Yahoo Finance.
An AI-assisted research workbench for A-shares, US and HK stocks, with watchlists, portfolio ledger, daily market review, stock deep-dives, backtesting and a local report library.
MCP server giving AI assistants 39 tools for market data, technical analysis, screeners, backtesting and sentiment across crypto, stocks, forex and futures.
HTTP API and MCP server that exposes AKShare's financial data interfaces to any language or AI assistant like Claude and Cursor.
A starter vault, guide, skills and scripts for an AI agent that builds and maintains a linked markdown knowledge base in Claude Code and Obsidian.