Free Intensive Nov 21–22Free 2-day hands-on Vibecoding Intensive on Nov 21–22 at 16:00 MSK (Sat–Sun) · Live Cohort 3 starts Nov 23Join Free →Cohort 3 (Nov 23)
ReleaseCode / SDK · ActionableGitHub Trending AI→ original

Claude Code Taught to Help Investors: Market Review Takes 15 Minutes a Day

Claude Code is Anthropic's AI assistant for working with files and code, and Skills are folders of instructions and scripts that it picks up when a task calls for them. The developer tradermonty has assembled a set of these skills for retail investors: three skills take 15 minutes a day to assess how broadly the market is rising and how much risk is acceptable right now. The set places no orders. The decision stays with the human, and for developers it shows how to package a working routine into skills.

AI-processed from GitHub Trending AI; edited by Hamidun News
Claude Code Taught to Help Investors: Market Review Takes 15 Minutes a Day
Source: GitHub Trending AI. Collage: Hamidun News.
Listen to article
Article Fact Sheet & Key Figures
ParameterDetails
Primary sourceGitHub Trending AI ↗
Editor-in-Chief
MIT licensethe code can be freely taken and modified
Key metric #2Screeners need FMP, the portfolio needs Alpaca; the fallback is CSV
Key metric #3The starter five skills run on public CSVs and screenshots, with no API keys

Claude Code is Anthropic's AI assistant that works with files and code on your computer. Skills are folders of instructions, checklists, and scripts: Claude picks up the relevant folder when a task fits it. The tradermonty/claude-trading-skills repository has assembled these folders into a working set for retail investors.

Today it has gained about 60 stars on GitHub Trending. The headline number in the project's promise is 15 minutes: that is how long the daily market check takes along the ready-made route of three skills. These skills look at what share of stocks are currently in an uptrend and suggest how much risk to take on.

The author started the project for personal use and released it under the MIT license.

What's Inside and Who It's For

The set is aimed at people who don't have time to sit over charts. The basis of their portfolio is long-term investing, ETFs, and dividend stocks. Short swing trades (lasting a few days or weeks) are offered as an additional strategy, and only when the market allows it. Scalping and fully automated trading are not part of the target audience.

The author states directly: the goal is not to hand buying and selling decisions over to AI. The task is more modest: to organize market review, risk control, trade planning, the journal, and the analysis of mistakes. This is not a signal service, not a brokerage platform, and not financial advice. The set does not place orders or run hidden scheduled tasks, and the decisive steps remain with the human.

The catalog is large: dozens of individual skills. Among them are market breadth analysis (what share of stocks is rising together with the index), stock screeners based on the Minervini and O'Neil methods, a position size calculator, dividend portfolio monitoring, a trade journal, and a review of past signals. The main list of skills is kept in a separate index, and if it conflicts with the description, the index is the authority.

How It Works in Practice

Newcomers are offered to start with a ready-made route. Each route is described by a machine-readable manifest: it lists the skills in order, the decision points, and the outputs.

  • A 15-minute daily market check: market-breadth-analyzer, uptrend-analyzer, and exposure-coach. The result is a recommendation on how much risk is acceptable right now, not an order.
  • A weekly review of the long-term portfolio. This requires the Alpaca brokerage service; manual CSV upload serves as a simplified substitute.
  • Searching for swing candidates only when risk is allowed. Drawdown and discipline are checked first, then position size. Screeners require the FMP market data service.
  • A journal of closed trades and a monthly review of results with rule adjustments.

An example on the fingers. If you have several losing trades in a row, the drawdown-circuit-breaker skill (a "drawdown circuit breaker") will stop you before you open a new position. The pre-trade checklist will not let an entry through without a plan or with an oversized position. This is the discipline people usually lose first.

Limitations and Conclusion

The free start is not enough for everything. The minimal path of five skills works on public CSVs, chart screenshots, and local files, without paid APIs. But "no API" does not mean "no external data": the data still has to come from somewhere. FMP, FINVIZ Elite, and Alpaca connect as optional integrations for specific scenarios.

There are also access conditions. Skills in the web version of Claude are available on the Free, Pro, Max, Team, and Enterprise plans, but Claude Code is not included in the free Claude.ai tier, and Anthropic's terms may change. In Claude Code, a skill is installed by copying the folder into the skills directory. For the web version, there is a script that packs it into a ZIP. Separately, there is a companion for the Hermes agent mode with slash commands such as /monthly-performance-review.

The authors repeat: backtests, screenings, and AI analysis do not guarantee future results, and responsibility for decisions rests entirely with the user. For the average reader, this is a reason to see the project as a constructor for a process, not a source of profit.

The practical takeaway goes beyond trading. The repository shows a mature way of building skills for LLMs: with manifests, a metadata schema, a validator in CI, clear stopping points, and honest caveats. If you are building agents for finance, medicine, or any field where an error is costly, this structure is worth examining and adopting: the human makes the decision, while the AI prepares the data and reminds you of the rules.

Story

Key Questions Answered

What's Inside and Who It's For?

The set is aimed at people who don't have time to sit over charts. The basis of their portfolio is long-term investing, ETFs, and dividend stocks. Short swing trades (lasting a few days or weeks) are offered as an additional strategy, and only when the market allows it. Scalping and fully automated trading are not part of the target audience. The author states directly: the goal is not to hand buying and selling decisions over to AI.

How It Works in Practice?

Newcomers are offered to start with a ready-made route. Each route is described by a machine-readable manifest: it lists the skills in order, the decision points, and the outputs. A 15-minute daily market check: market-breadth-analyzer, uptrend-analyzer, and exposure-coach. The result is a recommendation on how much risk is acceptable right now, not an order. A weekly review of the long-term portfolio. This requires the Alpaca brokerage service; manual CSV upload serves as a simplified substitute.

What are the key details on Limitations and Conclusion?

The free start is not enough for everything. The minimal path of five skills works on public CSVs, chart screenshots, and local files, without paid APIs. But "no API" does not mean "no external data": the data still has to come from somewhere. FMP, FINVIZ Elite, and Alpaca connect as optional integrations for specific scenarios. There are also access conditions.

ZK
Zhemal Khamidun — CPO at Alpina Digital, product manager of AlpinaGPT. Building AI products since 2019. Hamidun News is a pet project that grew into a production aggregator with 6,000+ readers.
✦ Hands-On AI Engineering · Hamidun Academy

Build & Ship Production AI Agents Without Boilerplate Code

Start your free 72-hour trial at Hamidun Academy (academy.hamidun.com) — interactive lessons on Claude Code & Cursor, live Tech Radar, and production agent templates.

Start 72h Free Trial →Vibe-Coding Intensive
What do you think?
Loading comments…