---
title: "Claude Day Trader Skill: What the 11 Skills Do and Don't Do"
date: "2026-10-26"
video_id: "7701015064433806623"
tiktok_url: "https://www.tiktok.com/@techesha/video/7701015064433806623"
creator: "@techesha"
category: "Finance"
tags: ["claude", "claude skills", "day trading", "trading bot", "alpaca"]
excerpt: "The Claude day trader skill is 11 free slash commands. It never trades on its own, and its time machine runs 10,000 simulations, not every possible outcome."
---
The Claude "trader skill" is a free, MIT-licensed pack of 11 Claude skills for day trading, published on GitHub as day-trader-skill by Jake Schincariol. It scans charts, tracks news and times entries, but it does not make winning trades automatically. Every order needs a risk check and your approval in chat, and paper trading is the default.

A TikTok from @techesha claims the pack lets you "make winning trades automatically" and that its time machine skill "replays every possible outcome of the trade". The repo's README says something narrower on both points.

## What is the Claude trader skill?

The repository [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill) contains 11 skills, each invoked as a slash command:

- `/trader-scanner`, `/trader-news` and `/trader-entry` for scanning charts, tracking breaking news and timing an entry
- `/trader-exit`, `/trader-risk` and `/trader-budget` for exits, risk checks and position sizing
- `/trader-timemachine` for replaying a trade before you take it
- `/trader-broker` for sending orders through Alpaca
- `/trader-alerts`, `/trader-analyst` and `/trader-pelosi` for alerts, earnings analysis and congressional trade tracking

The video names only the scanner, news, entry and time machine skills. An [OrcaRouter blog post](https://www.orcarouter.ai/blog/claude-day-trader-skill-what-it-actually-does) dated 2026-10-23 describes the same structure: eleven instruction files, eleven small Python tools and a `trader/` folder where each step leaves notes for the next. It says the repository appeared on GitHub on 2026-10-20.

The video never shows a repo name. The match rests on the 11-skill count, the skill jobs and the time machine graphics, which is strong evidence but not proof that this is the exact repo.

## Is the Claude trader skill free?

The repository is free. The README lists an MIT license, no signup, and free public data sources: Yahoo Finance chart data, Nasdaq Trader symbol lists, SEC EDGAR and the House Clerk.

That covers the code only. I did not check what a Claude plan costs or whether an Alpaca account carries fees. The README also notes that the Yahoo endpoint is unofficial and can lag or rate-limit, so the scanner's view of the market can be behind.

## Does it make trades automatically?

No. The README says nothing in the pack places an order on its own. Orders go only through `/trader-broker`, after `/trader-risk` passes the order and the user approves it in chat. The broker skill connects to Alpaca's MCP server with paper trading as the default. The OrcaRouter post quotes the README line "No trade goes through until you say yes."

Nothing in the README or the blog promises winning trades. The README's disclaimers say it is not financial advice and that most day traders lose money. They add that stops are not guaranteed fills and that the tool does not account for taxes, wash sales or pattern-day-trader rules. The OrcaRouter post states that no audited track record exists.

The video's opening line, that Claude "just killed day traders", has no support in either source.

## Does the time machine replay every possible outcome?

No. Before a trade, `/trader-timemachine` simulates the rest of the session 10,000 times. Each simulated 5-minute candle is drawn from the stock's own candles at the same time of day over the previous 59 sessions, using a fixed seed of 19 so the results can be reproduced. It also reruns the same rule on those 59 real sessions.

In the README's TSLA example, about 29% of simulations hit the target first, 26% hit the stop first and 45% were still open at the close. The historical rerun fired 33 times, with 13 targets, 15 stops and 5 neither. The author calls the result close to a coin flip. OrcaRouter gives the same split as 29.4%, 25.5% and 45.1%.

The README warns that the simulation uses only about 60 days of data and cannot anticipate events such as earnings or halts. Resampling 10,000 paths from 59 sessions produces an estimate. It does not enumerate every outcome, and the README does not claim the "most accurate statistics" that the video promises.

The video also shows a chart titled "How the 10,000 replays end" with "Target first 10.9%" and "Stop first 0.0%". Those numbers do not match the README example, and the video does not name the ticker or date, so treat the chart as an illustration of the output format.

## Is it comparable to Bloomberg software?

The video says the time machine is "the same type of software Bloomberg charges thousands for". I found no Bloomberg product or price for a trade-replay tool to compare against. The README describes a resampling script that reads free Yahoo data, which is a much smaller tool than a Bloomberg Terminal.

## What about the presenter's own results?

The presenter says she trades with a similar setup and shows a "Claude Trading Bot" card with equity growing from $100.00 to $157.33, a gain of 57.33%. The card has no broker name, statement, trade list or link, and it does not say whether the money is real or paper. The video also shows animated explainer graphics rather than the skills running in Claude.

## Bottom line

The day-trader-skill repo is real, free and has 11 skills. It requires your approval for every order and defaults to paper trading. Its time machine is a 10,000-run simulation built from 59 recent sessions, and in the author's own TSLA example it came out close to a coin flip. Treat the video's "winning trades" and "every possible outcome" claims as marketing.

## Sources

- [day-trader-skill on GitHub (Jakeschincariol)](https://github.com/Jakeschincariol/day-trader-skill): skill names, license, data sources, approval flow, replay method, TSLA example and disclaimers.
- [Claude day trader skill: what it actually does, OrcaRouter blog, 2026-10-23](https://www.orcarouter.ai/blog/claude-day-trader-skill-what-it-actually-does): independent description of the eleven skills, replay figures and the lack of an audited track record.
- [TikTok post by @techesha](https://www.tiktok.com/@techesha/video/7701015064433806623): the video that made the claims.


## Video description and verification notes

**The file is a 35.805 s vertical clip (1080x1920, MP4/ISOM container) with an HEVC Main video stream at 30 fps and about 1.29 Mbps. The audio is HE-AACv2 stereo at 44.1 kHz and about 64 kbps. The container totals 6,103,941 bytes at roughly 1.36 Mbps. ffprobe gives 35.800 s for video and 35.805 s for audio. The post timestamp is epoch 1793032307, which is 2026-10-26 16:31:47 UTC. The uploader handle is @techesha (nickname "TechEsha"), and the audio credit is "original sound" by TechEsha. The description is 62 characters: "If you want the repo for this let me know 👇👇 #aitools #sidehustle". The archive captured these counts on 2026-10-27 at 19:35 UTC: 125,100 views, 9,177 likes, 33 comments, 1,080 reposts and 6,645 saves. I read nine frames: 1, 4, 6, 8, 10, 12, 14, 16 and 18. Frame N sits at roughly (N-1)×2 s. Frame 1 is a split screen. A woman in a red zip top, arms crossed, sits at the right under a white pill caption "Yay or Nay?". A young man talks to camera at the lower left. An inset pixel-art desk scene with a tombstone marked "RIP" carries the caption "DAY TRADERS". Frame 4 shows the woman holding a rose-gold laptop with yellow text "IS IT YAY OR NAY?". Frame 6 shows a dark "Chart Scanner" panel reading "1,240 of 5,259 US stocks" at "10:15 AM", with tickers such as AAPL, COP, CPNG and ELV checked, and the caption "THOUSANDS OF CHARTS". Frame 8 shows a candlestick chart with a green label "Get in 10:15 AM · $364.18", a blue "Range high" line at 362.18, and the caption "TO GET IN". Frame 10 shows the woman with an overlay titled "Claude Trading Bot" marked "LIVE": starting equity $100.00 dated "26 Jun 2026 · 20:00 UTC", current equity $157.33, realized $61.37, unrealized $0.00, total P&L "+$57.33" and "57.33%". Frame 12 shows a pixel-art vault scene with the caption "BEFORE YOU RISK". Frame 14 shows a bar chart titled "How the 10,000 replays end" with "Target first 10.9%", "Stop first 0.0%", a "Neither by 4 PM" row with no visible bar, and the caption "STATISTICS". Frames 16 and 18 show the woman with a "YAY or NAY" checkbox graphic. No terminal, Claude chat window, GitHub page or repo URL appears in any frame I read, and I did not read frames 2, 3, 5, 7, 9, 11, 13, 15 or 17. The transcript has 9 segments and about 150 words. The speaker argues that a free Claude "trader skill" made of 11 skills lets people make winning trades automatically, that the "time machine skill" replays every possible outcome and gives the most accurate statistics, that this is the kind of software Bloomberg charges thousands for, and she gives it a "yay". The last segment ends at 35.76 s against 35.805 s of audio, and all nine segments begin inside the audio, so there is no hallucinated tail.**

## The product is real, and the video's "trader skill" is a pack of 11 slash commands

At 3.6 s the video says "it's called the trader skill and it's completely free", and at 7.76 s that "it's not one skill either, it's 11 of them". The staged transcript renders Claude as "cloud" in several places (0.0 s and 3.6 s, for example) and as "claude" only in the final segment. The frames show pixel-art Claude-style mascot artwork and the word "Claude" in the bot overlay, so I read "cloud" as Whisper's mangling of "Claude".

The primary source I found is the GitHub repository [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill) by Jake Schincariol. Its README describes 11 Claude skills for day trading, invoked as `/trader-scanner`, `/trader-news`, `/trader-entry`, `/trader-exit`, `/trader-timemachine`, `/trader-risk`, `/trader-budget`, `/trader-broker`, `/trader-alerts`, `/trader-analyst` and `/trader-pelosi`. That confirms "11 of them". The video's three named jobs match the repo. The scanner scans charts (frame 6 shows the "Chart Scanner" panel), the news skill tracks breaking news, and the entry skill times the entry (frame 8, "Get in 10:15 AM · $364.18"). The README also names a congressional trade tracker, a risk manager, a position sizer, alerts, an earnings analyst and a broker executor, none of which the video mentions.

A second source, the [OrcaRouter blog post](https://www.orcarouter.ai/blog/claude-day-trader-skill-what-it-actually-does) dated 2026-10-23, describes the same structure: eleven instruction files, eleven small Python tools and a `trader/` folder where each step leaves notes for the next. It adds that the repository appeared on GitHub on 2026-10-20. The same blog calls the repo a sequel to an earlier trader-skill, so "the trader skill" in the video may point at either, but the 11-skill structure matches this one. The video never shows a repo name, so the match rests on the 11-skill count, the skill jobs, and the "time machine" replay graphics. I count that as strong but not proven identity.

On "completely free", the README lists an MIT license, no signup, and free public data sources: Yahoo Finance chart data, Nasdaq Trader symbol lists, SEC EDGAR and the House Clerk. The repository costs nothing. I did not check what a Claude plan costs or whether the Alpaca broker connection carries fees, so "free" holds for the repo only. The README also says the Yahoo endpoint is unofficial and can lag or rate-limit, which bears on how current the scanner's 1,240-of-5,259 view in frame 6 can be.

## "Make winning trades automatically" contradicts the README's approval gate

At 0.0 s the video says "you can now make winning trades automatically inside of cloud", and the opening line says Claude "just killed day traders". The README says otherwise about automation: nothing in the pack places an order on its own. Orders can only go through `/trader-broker`, after `/trader-risk` passes the order and the user approves it in chat. The broker skill connects to Alpaca's MCP server, with paper trading as the default. The OrcaRouter post quotes the README line "No trade goes through until you say yes." It also states that the pack is built that way by design and that no audited track record exists.

Nothing in the README or the blog promises winning trades. The README's disclaimers say it is not financial advice and that most day traders lose money. They add that stops are not guaranteed fills and that the tool does not account for taxes, wash sales or pattern-day-trader rules. The headline "killed day traders" is the video's own rhetoric, and I found no source supporting it. The frame 1 tombstone graphic labelled "DAY TRADERS" repeats that rhetoric without evidence.

## "Replays every possible outcome" and "most accurate statistics" overstate a 10,000-run simulation

At 24.64 s the video says the time machine skill "replays every possible outcome of the trade", and at 28.08 s that it "gives you the most accurate statistics of every possible outcome". The README describes a narrower method. Before a trade, `/trader-timemachine` simulates the rest of the session 10,000 times. Each simulated 5-minute candle is drawn from the stock's own candles at the same time of day over the previous 59 sessions, using a fixed seed of 19 so results can be reproduced. It also reruns the same rule on those 59 real sessions.

In the README's TSLA example the simulation showed about 29% hitting the target first, 26% hitting the stop first and 45% still open at the close. The historical rerun fired 33 times, with 13 targets, 15 stops and 5 neither. The author calls the result close to a coin flip. The OrcaRouter post gives the same split as 29.4%, 25.5% and 45.1%. The README warns that the simulation uses only about 60 days of data and cannot anticipate events such as earnings or halts. A resample of 10,000 paths from 59 sessions is an estimate, not an enumeration of every possible outcome. Nothing in the README claims it is the most accurate statistics available.

Frame 14 shows a chart titled "How the 10,000 replays end" with "Target first 10.9%" and "Stop first 0.0%". Those figures differ from the README's TSLA example, so they come from a different run, and the video does not name the ticker or date. A 0.0% stop-first reading next to a target-first reading of 10.9% would leave about 89% of runs in the "Neither by 4 PM" row, which has no visible bar in the frame. I did not find the source of this chart, so I treat it as an illustration of the output format. It does not establish how the tool performs.

## The Bloomberg comparison and the presenter's own trading results are unsourced

At 28.08 s the video says the time machine is "the same type of software Bloomberg charges thousands for". I did not find a Bloomberg product page or price for a trade-replay tool. The README describes a Monte Carlo-style resampling script that reads free Yahoo data. The comparison is unverified, and a free script that resamples recent 5-minute candles does not match the scope of a Bloomberg Terminal as a product. I did not fetch Bloomberg pricing, so I make no price claim.

The presenter says at 15.76 s "i do trade with cloud and i run a very similar setup", and at 32.0 s that trading with Claude is "absolutely possible ... because i do it". Frame 10 shows a "Claude Trading Bot" card with equity growing from $100.00 to $157.33 since "26 Jun 2026 · 20:00 UTC", a total gain of +$57.33 (57.33%). The card carries no broker name, account statement, trade list or link, and it does not show whether the money is real or paper. I cannot verify it. The README's own advice is that results from replays are not a track record, and the video gives no audited record either. A single small-balance gain over a few months does not show that the approach works.

The "yay" verdict at 35.76 s is an opinion. It also rests on an incomplete demo: the frames show animated explainer graphics for each skill, and no frame I read shows the skills running in Claude.

## Key Takeaways

- **Verified:** The pack has 11 skills. The repo [Jakeschincariol/day-trader-skill](https://github.com/Jakeschincariol/day-trader-skill) lists 11 `/trader-*` skills under an MIT license, including the scanner, news, entry and time machine skills the video names. I could not confirm from the video that this is the exact repo it uses, because no repo name is shown.
- **Correction:** At 0.0 s the video says you can "make winning trades automatically". The README says nothing in the pack can place an order on its own, and orders need `/trader-risk` clearance plus user approval in chat, with paper trading as the default.
- **Correction:** At 24.64 s the video says the time machine "replays every possible outcome". The README describes 10,000 simulated sessions resampled from the stock's previous 59 sessions at a fixed seed, plus a rerun on those 59 real sessions.
- **Partial correction:** At 3.6 s the video says it is "completely free". The repository is free under MIT with free public data sources, but I did not check Claude plan costs or Alpaca account terms.
- **Unverified:** The Bloomberg price comparison at 28.08 s and the presenter's "Claude Trading Bot" results (+$57.33 on $100.00 in frame 10) have no source in the video or in any page I read.
- **Context:** The README's TSLA example gives roughly 29% target first, 26% stop first and 45% open at the close, and the author calls the historical rerun close to a coin flip. The README also says most day traders lose money.

## Resources

- [day-trader-skill, GitHub (Jakeschincariol), fetched 2026-10-28](https://github.com/Jakeschincariol/day-trader-skill) establishes the 11 skill names, the MIT license, the free data sources, the approval-gated broker flow, the 10,000-run replay method over 59 sessions, the TSLA example results and the disclaimers I cite.
- [Claude day trader skill: what it actually does, OrcaRouter blog, 2026-10-23](https://www.orcarouter.ai/blog/claude-day-trader-skill-what-it-actually-does) establishes the independent description of the eleven skills, the replay figures (29.4%, 25.5%, 45.1%), the repo's appearance on GitHub on 2026-10-20 and the lack of an audited track record. It reports 637 stars as of 2026-10-23, while the GitHub page I fetched showed about 2.6k stars, so star counts vary between sources and dates.
- [TikTok post by @techesha, 7701015064433806623](https://www.tiktok.com/@techesha/video/7701015064433806623) is the video itself. Metadata, frames and transcript come from the staged artifact directory, not a live fetch.
