Skip to content
Get packs

Fundamental Stock Screener

Filters stocks by PE, PB, ROE and financial statement fields for backtest signals

Source Download skill
Repository
HKUDS/Vibe-Trading
Stars
37,433
Licence
MIT
Files
2 files

What it does

Once installed, the agent can build a value or growth stock screen using fundamental metrics such as price-to-earnings, price-to-book and return on equity. It turns those filters into long or flat signals for backtesting, covering A-shares via Tushare and US/HK stocks via yfinance. The skill also includes a Python example that screens tickers and a backtest-oriented engine for A-share data.

Great for

  • Quant researchers testing value or growth stock selection rules
  • Developers building backtests on A-share data with Tushare
  • Analysts who want a quick screen of US or HK stocks by valuation and profitability

Skip it if

  • Live trading decisions: yfinance Ticker.info is a snapshot and the skill does not validate data quality, so results can be wrong or stale
  • Historical US/HK daily backtests: the skill itself says yfinance cannot provide point-in-time time series, so results would be misleading
  • Investment advice for non-experts: the skill provides screening logic only, not a judgement on whether a stock is worth buying

Try asking

  • “Build a value screen for A-shares with PE below 15, PB below 2 and ROE above 10% over 2023 to 2024”
  • “Screen S&P 500 components for PE under 20, PB under 3 and ROE above 8%”
  • “Filter Hong Kong stocks by fundamentals and use the results as a stock universe for a technical strategy”
  • “Add revenue and net profit positivity checks to my A-share backtest using Tushare statement data”
Step-by-step guide: how to use Fundamental Stock ScreenerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    fundamental-filter.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip fundamental-filter.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip fundamental-filter.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Check the ROE units: Tushare uses percentages (15 means 15%) while yfinance uses decimals (0.15 means 15%)
  • Always filter out negative PE and handle NaN values before ranking, as the skill's pitfalls section warns
  • Treat screen results as a starting universe for further analysis rather than a final buy list

What's inside

  • example_signal_engine.py
  • SKILL.md

Redistributed unmodified from HKUDS/Vibe-Trading under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.