# Quant factor screen

Rank a stock universe with transparent QVeris factor evidence across quality, momentum, valuation, liquidity, volatility, and news risk.

## Agent Install Policy

Agents must get explicit user confirmation before installing a skill, writing configuration, or changing the local environment.

1. Read this guide and the manifest: https://qveris.cn/skills/qveris-quant-factor-screen/manifest.json
2. Explain to the user what will be installed and which QVeris API actions may be used.
3. Ask for explicit approval before running an install command or changing local configuration.
4. After approval, install the skill and run one starter prompt.

## Official GitHub Source

- Repository: https://github.com/QVerisAI/open-qveris-skills
- Skill path: qveris-quant-factor-screen
- Skill source: https://github.com/QVerisAI/open-qveris-skills/tree/main/qveris-quant-factor-screen
- Clone and inspect: `git clone https://github.com/QVerisAI/open-qveris-skills.git && cd open-qveris-skills/qveris-quant-factor-screen`

## Install Commands

- OpenClaw: `openclaw skills install qveris-quant-factor-screen`

## Starter Prompts

### Theme screen
Rank a theme universe by transparent factors.

```text
Use QVeris to screen 50 AI infrastructure stocks by quality, momentum, valuation, liquidity, volatility, and news risk. Return top 10, bottom 5, missing data, factor weights, QVeris calls used, and estimated credits.
```

### A-share screen
Build an A-share candidate list.

```text
Use QVeris to screen A-share semiconductor equipment stocks. Rank by growth, profitability, balance-sheet quality, liquidity, valuation, and recent catalysts.
```

### Factor audit
Explain why a name ranked high or low.

```text
Use QVeris to audit why this stock ranks high in a factor screen. Show the raw factor evidence, missing fields, and which factor dominates the score.
```

## QVeris API Actions

- Discover `POST /search`: Find quote, OHLCV, fundamentals, valuation, financial statements, news, and liquidity capabilities.
- Inspect `POST /tools/by-ids`: Check how many tickers each provider covers and estimate cost before batch calls.
- Call `POST /tools/execute`: Call selected inputs, normalize factors, and return ranks with missing-data warnings.

## Estimated QVeris Usage

This workflow usually needs 8-40 paid Calls after free Discover and Inspect preflight. Cost depends on providers, ticker count, and time window.

- Typical paid Call executions: 8-40
- Planning estimate: 8-400 credits
- Free actions: Discover, Inspect
- Paid actions: Call
- Note: Ask for explicit approval before paid Calls. Inspect billing_rule for every selected capability and reduce scope if the estimate is too high.

## Related Cases

- [Use FMP with QVeris](https://qveris.cn/blog/qveris-fmp-finance) - Turn structured financial data into callable agent capabilities.
- [Twelve Data market capabilities](https://qveris.cn/blog/qveris-twelve-data) - Add market data coverage for global research and screening workflows.
- [OpenClaw A-share finance assistant](https://qveris.cn/blog/openclaw-a-shares-finance-assistant) - A practical workflow for source-backed A-share monitoring.

## Human Page

https://qveris.cn/skills/qveris-quant-factor-screen