InvestSkill skill
InvestSkill gives an assistant 34 ready frameworks for analysing US stocks, from company valuation to portfolio risk
- 285 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Buy and sell conclusions can be wrong and do not replace advice from a professional.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/investskillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Buy and sell conclusions can be wrong and do not replace advice from a professional.
This is third-party code. Review the repository files before installing.
What it does
A set of 34 Markdown prompts for analysing US stocks. There is no runtime or API: each framework defines the order of analysis, and the assistant pulls data from whatever sources it has. A command such as `/us-stock-analysis:stock-eval AAPL` runs a ticker through a framework. The installer copies frameworks to `.investskill/prompts/` and wires the agent entry point: `.claude/skills` for Claude Code, `.cursor/rules` for Cursor, `GEMINI.md`, `AGENTS.md` for Codex and others. Claude Code also has a marketplace plugin. `--lang zh-TW` switches the answer to Traditional Chinese.
Who it is for. Retail investors who pick their own stocks and want one analysis checklist instead of scattered chat prompts.
Good fit when
- Before buying a stock you want the same pass every time: business quality, valuation, risks.
- A company report should become a structured summary.
- A portfolio is checked for concentration and decision discipline.
- You are learning to read financials and the frameworks suggest the order of questions.
Not a fit when
- You need live quotes: the frameworks have no market data connection.
- You plan to trade on a signal with no checking of your own.
- You care about Russian securities or markets other than the US.
Example request
Evaluate AAPL with the stock-eval framework and list separately the data you could not verify.Limitations
The frameworks cover US stocks. They do not load market data themselves, so figures depend on what the assistant can reach and should be checked against filings. Outputs such as a buy, hold or sell signal are model conclusions, not investment advice, and the README has a separate page on data accuracy. The `curl ... | bash` install runs a script from the internet: read `install.sh` first or use the marketplace plugin.
How to disable. Delete the `.investskill/` directory and the lines the installer added to `AGENTS.md`, `GEMINI.md` or `.cursor/rules/investskill.mdc`. The Claude Code plugin is removed with `/plugin uninstall`.
FAQ
Do I need API keys or a subscription?
No. The frameworks are Markdown and work with any assistant, including a free tier or a local model.
Does the skill trade?
No, it only analyses a company and writes a conclusion. Trades stay with you.
How do I install for Cursor?
Swap the flag: `-a cursor` creates `.cursor/rules/investskill.mdc`. Copilot, gemini, codex and opencode are also available.
How many frameworks are included?
34 structured frameworks. Three earlier skills remain as aliases so old references keep working.
Does it work in Russian?
The README documents English and Traditional Chinese (`--lang zh-TW`). The agent may answer in Russian, but the README has no dedicated support.
Discussion
No questions or reviews yet.
Related
SkillsA set of skills for individual investors and traders: market review, stock screening, technical analysis, trade planning, journaling and post-trade review
A set of investment research skills for Claude Code and Codex built on four investors' methodologies. It is a research tool, not investment advice
Claude plugin for reading investor filings, sizing portfolio positions and preparing orders for a separate brokerage connector
Four skills for China's A-share market: quotes and indicators, trend-pullback signals, a simulated account and backtests
Five skills for investment research: tech company earnings, value investing, market sentiment, US liquidity and the Bitcoin cycle
Thirteen skills for quantitative trading on China's A-share market: AKShare and BaoStock data, Backtrader and RQAlpha backtests, QMT and JoinQuant docs
README in short
34 structured US stock analysis frameworks as prompts, with no runtime, keys or payments.