Finlab

This is a quantitative trading framework that connects Claude to FinLab's market data and backtesting engine across five markets (Taiwan, US, Korea, Japan, Hong Kong). It handles the full loop: pull price and fundamental data with `data.get()`, build factor conditions using DataFrame methods like `.rise()` and `.is_largest()`, combine them into position signals, then run `sim()` to backtest with realistic fees and slippage. The US market support is detailed, covering filing-date-aligned fundamentals and ETF rotation strategies. You'll need a FinLab API token (free tier gives 500MB daily). The workflow is clean if you're comfortable with pandas-style operations, though the documentation leans heavily on Taiwan market examples.

skills.sh installs: 2K
GitHub stars: 426
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add koreal6803/finlab-ai --skill finlab --agent claude-code

Installs into .claude/skills of the current project.

Files

FinLab Quantitative Trading Package

Prerequisites

Before running any FinLab code, verify these in order:

uv is installed (Python package manager):
```
uv --version
```
If uv is not installed, tell the user to install it.

After installing, ensure uv is on PATH:
```
source $HOME/.local/bin/env 2>/dev/null  # Add uv to current shell
```
FinLab is installed via uv (requires >= 2.2.15):
```
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):
```
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 — a hosted Jupyter environment with finlab preinstalled and your account already logged in.
Logged in to FinLab (finlab >= 2.0; no legacy API token required):

SKILL.md on GitHub

Details

Repository: github.com/koreal6803/finlab-ai
Categories: Documentation, Finance & Trading
First seen: Apr 16, 2026