Key takeaways

  • A free, open-source toolkit of Claude skills for individual investors: market review, risk checks, trade planning and journaling.
  • It says plainly that the goal is not to outsource buy and sell decisions to AI. Human decision gates stay central.
  • Journaling is local, and position sizing is described as a pure calculation, so the routine is yours to inspect.
  • The catches: it is not financial advice, not a signal service, and some workflows use optional data or broker integrations.
  • We did not test any trading outcomes, and nothing here is a recommendation to buy or sell.

What it is

Claude Trading Skills describes itself as a Claude Skills-based trading workflow toolkit for time-constrained individual investors. It is open source under the MIT licence, and the code is on GitHub at tradermonty/claude-trading-skills.

The problem it solves

Busy investors often review markets and trades in an ad hoc way. The author says the project began as a personal effort to improve their own trading process with AI.

Its stated goal is not to outsource buy and sell decisions to AI, but to structure market review, risk management, trade planning, journaling and continuous improvement.

What you get

  • A structured routine: skills aimed at market review, risk management and trade planning rather than stock tips.
  • Position sizing as a pure calculation, according to the project, so you can see what it does.
  • Local journaling: a skill for recording decisions in local YAML files, so you can review them later.
  • Human decision gates: the project says they remain central.
  • Example outputs you can look at first, which use fictional data.

The catches

  • Not advice: the README says it is not financial advice, a signal service or a broker execution platform, and that trading involves risk, including loss of principal.
  • Not automation: it is not designed for fully automated trading, signal outsourcing or short-term scalping.
  • Integrations: FMP, FINVIZ Elite and Alpaca are optional, and one weekly workflow requires Alpaca, with a manual CSV as a degraded fallback.
  • No API does not mean no data: those skills still need public CSVs, chart screenshots or local files.
  • Account and warranty: Claude Code has separate account requirements, and the project is provided as is, without warranty.
  • Previews are illustrations, not live market readings or trading instructions.

What we did not test

We did not run any skill, connect any data service or broker, or test any trading outcome. This is not financial advice. Every claim here comes from a literal quote in the project's README or the GitHub API, and the feature descriptions are the project's own.

Verdict

Editors' view: this suits investors who already use Claude and want a more disciplined review and journaling routine. It is not a source of trade ideas, and it cannot promise any result. If you try it, start with the example outputs and keep every decision your own.

Repository
tradermonty/claude-trading-skills
Python · MIT
View on GitHub ↗

Sources

Need help adopting this, or have a software project in mind?

Tell us what you are building. The initial consultation is free. Email [email protected] or follow @zolnaltd.

Start a conversation →