FinLab AI skill
A skill connects agents to FinLab data and its Python engine for stock research and local historical strategy backtesting.
- 424 ★ on the repository
- Last commit
Broad access
Why this level
- The skill documents broker APIs for real orders that can lose money.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/finlab-aiDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The skill documents broker APIs for real orders that can lose money.
This is third-party code. Review the repository files before installing.
What it does
FinLab AI instructs an agent to obtain market data, develop a strategy and test it over historical periods. It helps install FinLab, sign in and run calculations locally, with primary examples covering Taiwan and US stocks. The skill is documentation without its own hooks or bundled programs. A separate hosted MCP only reads catalogs, strategies and references. The skill also documents broker APIs; an agent must preview each real order and wait for user confirmation.
Who it is for. For FinLab users researching trading hypotheses through an agent and verifying calculations against source data.
Good fit when
- Retrieve data for a research hypothesis.
- Backtest a strategy over historical periods.
- Compare metrics across calculation variants.
- Keep strategy code and results local.
Not a fit when
- You expect guaranteed future returns.
- Real orders would be sent without confirmation.
- You lack rights to the market data or broker account.
Example request
Prepare an educational FinLab backtest without broker access and show its calculation assumptions.Limitations
Calculations require Python 3.10 or later, uv and your own FinLab sign-in; data availability depends on the account. Backtests are sensitive to publication dates, fees and universe selection, so inspect those conditions before comparisons. Broker APIs can place real orders and lose money; begin without a trading connection. Order confirmation is mandatory, but independently verify the instrument, quantity and execution conditions before approving.
How to disable. Remove the skill or plugin and disconnect any broker credentials. Removing instructions does not cancel placed orders; inspect them separately in the broker account.
FAQ
Does the skill run its own daemon?
No. It contains documentation guiding the agent to a Python package.
How do I sign in?
`python -m finlab login` opens a browser.
What does hosted MCP do?
It reads strategies, data catalogs and documentation rather than sending orders.
Where does strategy code run?
On the user’s computer.
Is it an official FinLab project?
The README identifies FinLab AI as an official FinLab product.
Discussion
No questions or reviews yet.
Related
SkillsA skill that answers probability questions from market data: prediction markets, rates, yields and derivatives
Skills and an MCP server for options traders: quotes, technical analysis, Greeks, spreads, scanners and Interactive Brokers portfolio
A skill that queries Arkvol for China, Hong Kong and US market data and retells it with the date, indicators and limits of use
A set of skills for individual investors and traders: market review, stock screening, technical analysis, trade planning, journaling and post-trade review
A set of installable finance skills for the agent: news, stock data, sentiment, forecasting, signals, reports and search
A skill that finds bottlenecks in an industry's supply chain and shortlists A-share, Hong Kong and US stocks with data checks
README in short
Skill installation and read-only MCP setup are separate routes. Trading permissions come from an additional broker connection.
README badge
Original SKILL.md
--- name: finlab description: "Backtest and research stock strategies with the FinLab Python package on real market data: Taiwan stocks (台股) first, plus US, KR, JP, HK equities and ETFs/funds. Use whenever the user wants to backtest a strategy, screen stocks, or pull Taiwan stock data such as adjusted prices, monthly revenue, financial statements or institutional flows, even if they never name FinLab: 台股回測, 股票回測, 回測, 選股, 選股策略, 量化交易, 程式交易, 月營收, 三大法人, 財報, 美股回測, backtesting, trading strategies, stock data, stock selection, FinLabDataFrame, factor analysis, quant trading, US equity, S&P 500 / NASDAQ 100, SPY / QQQ, sector or leveraged ETFs, ETF rotation, 美股, or stock market analysis. Includes data access, strategy development, backtesting workflows, best practices, and US-market specifics (data availability map, filing-date-aligned quarterly fundamentals, US universe construction, USMarket vs. USFundMarket defaults, and ETF backtesting)." compatibility: Requires Python 3.10+ and uv package manager (https://docs.astral.sh/uv/) --- # FinLab Quantitative Trading Package ## Prerequisites **Before running any FinLab code, verify these in order:** 1. **uv is installed** (Python package manager): ```bash uv --version ``` If uv is not installed, tell the user to install it. After installing, ensure `uv` is on PATH: ```bash source $HOME/.local/bin/env 2>/dev/null # Add uv to current shell ``` 2. **FinLab is installed via uv** (requires >= 2.2.15): ```bash uv python install 3.12 # Ensure Python is available (skip if already installed) uv pip install --system "finlab>=2.2.15" 2>/dev/null || uv pip install "finlab>=2.2.15" ``` **Or use `uv run` for zero-setup execution** (recommended for one-off scripts): ```bash uv run --with "finlab" python3 script.py ``` `uv run --with` auto-creates a temporary environment with dependencies — no venv management needed. **Prefer zero-install?** Run notebooks directly in [FinLab Studio](https://studio.finlab.finance) — a hosted Jupyter environment with `finlab` preinstalled and your account already logged in. 3. **Logged in to FinLab** (finlab >= 2.0; no legacy API token required):