skilld
All skills
tradermonty avatar

/us-undervalued-growth-screener

@b9ca9a4
by tradermontytradermonty/claude-trading-skills2.9k stars
663

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.

Ask your Agent

Use this Skill: https://skilld.dev/gh/tradermonty/claude-trading-skills/us-undervalued-growth-screener

This session only. Nothing lands on disk.

referencesmigration-v3.2-to-v3.3.md

≈518 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Migration v3.2 → v3.3

Why v3.3 Exists

A live run intended for v3.2 was generated by a stale v3.1 runtime. Subsequent review also found that forecast bridges could be circular, commercial biopharma aliases could bypass LOE stress, peak-profit risk could avoid normalization, and data quality could remain too high without cash, TTM-period, ROIC, or EBITDA evidence.

v3.3 makes those failures mechanically detectable.

Breaking Changes

skill version: 3.3.0
snapshot schema: 3
screening audit schema: 3
contract revision: 3.3
runtime fingerprint: ug-v3.3-driver-bridge-bounded-pool-20260828

Old audits and snapshots are not resumable. Regenerate them.

Required Changes

  1. Replace the complete skill directory and .skill package from the same release.
  2. Verify all helper scripts with --version.
  3. Regenerate listing, discovery, broad-screen, checkpoint, and final artifacts.
  4. Add runtime metadata to every audit/snapshot.
  5. Add a valid generation audit for bounded pools.
  6. Rebuild forecasts from operating drivers rather than a preselected numerator.
  7. Add TTM-period source IDs, cash classification, ROIC/EBITDA evidence, and sector/cycle evidence.
  8. Use normalized commercial_biopharma sector semantics or a supported alias.
  9. Rerun all tests and the strict final smoke test.

Candidate Data Changes

  • Forecast drivers now require sufficient information to independently calculate the metric.
  • Adjusted forecasts must tie both GAAP and adjustment portions to the reconciliation.
  • Cash classification records corporate_cash, eligible marketable securities, restricted/customer funds, and normalization method.
  • TTM cash-flow methods require source IDs for reported TTM or each construction period.
  • peak_profit_risk=true requires normalization.
  • Commercial biopharma requires product concentration and LOE evidence.

Package Migration

Delete any installed same-name older skill before installing v3.3. Confirm the package SHA-256 and --version output after installation. Do not trust a filename alone.

Source: SKILL.md on GitHub

Third-party checks

No alerts5d3 checks · Risk SAFE
  • Gen Agent Trust Hub5d

    The skill is a professional-grade stock screening tool that implements rigorous data integrity checks and professional financial modeling. It uses local Python scripts to handle large data payloads from well-known financial APIs (Financial Modeling Prep and the SEC), keeping raw data out of the AI's immediate context. Security features include proactive filtering to prevent the inclusion of secrets or environment files in generated audit bundles.

  • Socket5d

    No alerts

  • Snyk5d

    Risk: LOW · No issues

Provenance

Signed by skilld at b9ca9a4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 18 hours ago.

Activeupdated last week

README badge

README badge for tradermonty/claude-trading-skills/us-undervalued-growth-screener