# AI use cases for Day Trader Skill (Jakeschincariol/day-trader-skill)

Repo: [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill) | Use cases: 3 | Page: https://dedupedai.com/use-cases/jakeschincariol-day-trader-skill/

The Day Trader skill is a pack of 11 Claude skills for day trading research: a chart scanner, news monitor, entry timer, exit planner, a Time Machine that replays a trade 10,000 times, risk and budget checks, price alerts, an earnings analyst, a Congress trade tracker and an order executor. The tools are plain Python on free public data, nothing can place an order on its own, and paper trading is the default. Not financial advice: paper trade first, and remember you can lose money.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Scan thousands of stocks for opening-range breakouts: https://dedupedai.com/use-cases/jakeschincariol-day-trader-skill/scan-for-opening-range-breakouts-with-claude/
- Replay a trade 10,000 times before you take it: https://dedupedai.com/use-cases/jakeschincariol-day-trader-skill/replay-a-trade-10000-times-before-you-take-it/
- Paper trade with a human yes on every order: https://dedupedai.com/use-cases/jakeschincariol-day-trader-skill/paper-trade-with-a-human-yes-on-every-order/

## How to scan thousands of stocks for opening-range breakouts with Day Trader Skill

Repo: [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install the skills and have Claude scan the US universe for setups, then pull the news on the hits.

**Who it is for:** A part-time trader who cannot watch thousands of charts at the open but wants a shortlist with context.

**The problem:** Finding setups by hand means flipping through charts and headlines while the move is already happening.

**The outcome:** A shortlist of stocks that broke their opening range, with the morning's headlines and filings for each.

### Steps

1. In Claude Code run `/plugin marketplace add Jakeschincariol/day-trader-skill` then `/plugin install day-trader-skill@day-trader-skill`
2. Or copy the folders: `cp -r day-trader-skill/trader-* ~/.claude/skills/` after cloning
3. Run `/trader-scanner`, or the tool directly: `python3 trader-scanner/scan.py orb --at 10:15`
4. Run `/trader-news` on the hits, for example `python3 trader-news/news.py --tickers TSLA --hours 12`
5. Add your name and email as sec_user_agent in trader/config.json so the SEC tools work

### Prompt to paste into your agent

```text
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.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jakeschincariol-day-trader-skill/scan-for-opening-range-breakouts-with-claude/

## How to replay a trade 10,000 times before you take it with Day Trader Skill

Repo: [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Set the stop and target first, then let the Time Machine show the honest odds from the stock's own history.

**Who it is for:** A trader who wants a reality check on a setup before risking money on it.

**The problem:** Gut feel says a setup looks great; nobody checks how the same rule did on the last 60 sessions.

**The outcome:** Simulated odds of hitting the target, the stop or neither, plus how the same rule did on past real sessions, and a position sized to your max loss.

### Steps

1. Set the plan before entry: `python3 trader-exit/exit.py plan --stop or-mid --target 1R --write`
2. Replay it: `python3 trader-timemachine/timemachine.py run --write`
3. Size the position to your budget and max loss: `python3 trader-budget/size.py --write`
4. Check it against your limits: `python3 trader-risk/check.py` returns PASS or BLOCK with the reason

### Prompt to paste into your agent

```text
Using Jakeschincariol/day-trader-skill, plan a trade on <ticker> with the stop at the opening range midpoint and a 1R target, run the Time Machine, size it for a <budget> account with a <max loss> max loss, and run the risk check. Report the odds and PASS or BLOCK, and do not send any order.
```

### Caveat

The Time Machine is a simulation built from the last 60 days of bars, not a prediction, and a stop can fill well past its price in a fast market. Not financial advice: paper trade first, and remember you can lose money.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jakeschincariol-day-trader-skill/replay-a-trade-10000-times-before-you-take-it/

## How to paper trade with a human yes on every order with Day Trader Skill

Repo: [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill) | Difficulty: Advanced | Time: 1 hour | Basis: From the README

Route approved orders to a paper brokerage account, with a risk check and your typed yes before anything goes out.

**Who it is for:** Someone who wants to practise day trading with an AI helper but never let it trade on its own.

**The problem:** Letting an agent near a brokerage account is scary when one wrong call can place a real order.

**The outcome:** Bracket orders on a paper account that only go out after the risk check passes and you approve that exact order twice.

### Steps

1. Keep `"paper": true`, the default in config.example.json
2. Connect a brokerage tool such as Alpaca's MCP server, which defaults to its paper account; keep keys in environment variables
3. In Claude set the brokerage tool to Needs approval, never Always allow
4. Run `/trader-broker`, read the ticket with `python3 trader-broker/ticket.py show`, and type yes only for the exact order
5. Add alerts for the stop, target and close with `python3 trader-alerts/alerts.py add --from-plan`

### Prompt to paste into your agent

```text
Set up Jakeschincariol/day-trader-skill with a paper brokerage account only. For <ticker>, show me the order ticket after the risk check and wait for my yes. Confirm in writing that paper is true before anything is sent.
```

### Caveat

The README notes most people who day trade lose money, and options, margin, shorting and leverage stay off unless you turn them on. Not financial advice: paper trade first, and remember you can lose money.

Risk, credentials: Brokerage keys belong in environment variables, never in the chat, and the connector should stay on the paper account.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jakeschincariol-day-trader-skill/paper-trade-with-a-human-yes-on-every-order/