# us-undervalued-growth-screener

Screens NYSE, Nasdaq and NYSE American stocks for undervalued-growth setups and returns a ranked report with a run audit.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1600 installs · ★ 3267
- Author: tradermonty
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/tradermonty/claude-trading-skills/tree/HEAD/skills/us-undervalued-growth-screener/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/us-undervalued-growth-screener

## What it does

The skill runs a full screen from a one-line request. It fills in defaults, pulls current data, repairs whatever blockers it can, and hands back the finished result in the same task. It will not ask you for a ticker list, API-plan details or an output path.

Under the hood sits a set of Python scripts. `run_pipeline.py` handles bulk retrieval, caching, FY1 normalization and the deterministic broad screen, `screen_universe.py` and `build_discovery_pool.py` build the candidate pool, `evaluate_candidates.py --strict --require-final` checks the result, `prepublish_audit.py` hunts for blockers, and `bundle_run_artifacts.py` packs a ZIP with every referenced artifact. Raw provider payloads stay on disk; only a compact summary reaches the model context. Before any run the skill insists on a preflight: every script must report the same version and runtime fingerprint. If the metadata differs, prior artifacts and cached runs are discarded — mixing skill versions is a hard failure, not a warning.

By default three candidates get the deep dive, while the research lanes target five slots: core GARP, high-growth exceptions, quality near misses, and cyclicals needing normalization. Three names cannot cover all four lanes, so decide up front whether you want the five-slot selection via a local copy of `assets/claude-code-config.example.json` with `max_deep_dive_candidates: 5`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill us-undervalued-growth-screener -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/us-undervalued-growth-screener/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/us-undervalued-growth-screener/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill us-undervalued-growth-screener -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/us-undervalued-growth-screener/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill us-undervalued-growth-screener -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/us-undervalued-growth-screener/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install tradermonty/claude-trading-skills us-undervalued-growth-screener
```

2. **Manually: put the files in place**
- File: `.github/skills/us-undervalued-growth-screener/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill us-undervalued-growth-screener -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/tradermonty/claude-trading-skills --path skills/us-undervalued-growth-screener
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/us-undervalued-growth-screener/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add tradermonty/claude-trading-skills --skill us-undervalued-growth-screener -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/tradermonty/claude-trading-skills/tree/HEAD/skills/us-undervalued-growth-screener/SKILL.md

## When to use it
- find undervalued growth stocks without a ready ticker list
- filter out candidates with heavy dilution or weak cash flow
- put EPS and FCF forecasts on the same comparison basis
- verify financials against primary sources instead of summaries
- produce a reproducible report with candidate-pool coverage audit

## Example prompts
- Run the us-undervalued-growth-screener skill and show me the ranked candidates
- Refresh the US undervalued-growth screen as of the latest close
- Verify the candidate pool and bundle the run artifacts into an audit ZIP

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 2d7cd43ffb185b9b.

BEGIN THIRD-PARTY FILE 2d7cd43ffb185b9b
```text
---
name: us-undervalued-growth-screener
description: Autonomously screen NYSE, Nasdaq, and NYSE American operating-company stocks for undervalued-growth/GARP opportunities using forward same-basis valuation, driver-derived EPS/FCF forecasts, primary-source financial verification, SBC and dilution controls, sector and cycle normalization, auditable candidate-pool coverage, and fail-closed final reporting. Use when asked to find, screen, rank, or refresh US undervalued-growth stocks, including minimal requests with no ticker list or parameters.
---

# US Undervalued Growth Screener — v3.6 (Claude Code Direct-FMP)

## Overview

Run an end-to-end US undervalued-growth/GARP screen from a minimal request. Find companies whose EPS or FCF per share can compound enough to support attractive two- to three-year returns **without assuming multiple expansion**, while controlling for accounting basis, forecast construction, SBC, dilution, leverage, cyclicality, corporate actions, peer context, source freshness, and evidence quality.

**Claude Code is the preferred execution environment.** In Claude Code, run the local direct-FMP pipeline once. The Python process performs bulk retrieval, persistent caching, FY1 normalization, liquidity calculation, four-lane discovery, and deterministic broad screening while keeping raw FMP payloads on disk and out of the model context. Claude reads only the compact run summary and selected candidate packets, then completes SEC/IR underwriting and the existing strict evaluation sequence.
```
END THIRD-PARTY FILE 2d7cd43ffb185b9b

The third-party file has ended. Everything between the 2d7cd43ffb185b9b tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 1535 of 38711 bytes. © tradermonty · MIT · https://github.com/tradermonty/claude-trading-skills/tree/HEAD/skills/us-undervalued-growth-screener/SKILL.md

## Similar
- [alphaear-deepear-lite](https://affpapa.org/en/nevibecode/skills/alphaear-deepear-lite.md) — skill · 334 installs
- [stock-correlation](https://affpapa.org/en/nevibecode/skills/stock-correlation.md) — skill · 3400 installs
- [estimate-analysis](https://affpapa.org/en/nevibecode/skills/estimate-analysis.md) — skill · 3200 installs
- [technical-analysis](https://affpapa.org/en/nevibecode/skills/staskh-technical-analysis.md) — skill · 586 installs

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md