All skills
tradermonty avatar

/us-undervalued-growth-screener

@b9ca9a4

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.

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

This session only. Nothing lands on disk.

referencesmigration-v3-to-v3.1.md

≈679 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Migration Guide — v3.0 to v3.1

Why v3.1 Exists

A v3.0 execution correctly refused to publish a ranking, but it failed operationally because it required near-complete financial coverage for the full market, silently used a reduced USD 10B–20B universe, selected unresolved sector-review rows using equal placeholder scores, and produced inconsistent selected/unprocessed state. The distributed standalone package also differed from the package embedded in the repository overlay.

Top-level snapshot schema: 3
Screening audit schema: 3 / contract revision 3.1
Run-state schema: 2
Skill version: 3.1.0

v3.1 keeps the strict primary-source, accounting, and forward-valuation controls while replacing the impossible market-wide financial-completeness requirement with a two-layer coverage model.

Required Changes

Screening artifacts

Old single artifact:

broad-screen-results.jsonl

v3.1 artifacts:

universe-audit-results.jsonl
broad-screen-results.jsonl
enrichment-queue.json
broad-screen-audit.json
broad-screen-shortlist.json

Audit metadata

audit_schema_version: 3
contract_revision: 3.1
candidate_pool_status: sufficient | no_qualifying_candidates | insufficient_data
selection_outcome: selected | no_candidates | insufficient_data

Checkpoint attachment

Replace the legacy single --artifact invocation with:

--universe-artifact .../universe-audit-results.jsonl \
--candidate-artifact .../broad-screen-results.jsonl

Plan-gated fundamentals

Do not abandon the run or demand a paid endpoint. Build a transparent stratified discovery pool with build_discovery_pool.py, enrich that bounded pool with available estimates/fundamentals, and rerun screen_universe.py.

Status migration

v3.0 behavior v3.1 behavior
Missing full-universe financial fields counted as global audit failure Missing candidate-pool economics become needs_enrichment
Review-only rows could share a placeholder score Review rows use broad_score=null and cannot be selected
Listing-only pool could be mistaken for no candidates insufficient_data; final no-candidates conclusion prohibited
Reduced provider scope could continue Scope marked incomplete; final contract blocked
Selected count could disagree with unprocessed state unprocessed = selected - verified invariant enforced

Package Migration

  1. Replace the entire skill directory; do not mix v3.0 and v3.1 scripts or assets.
  2. Start a new run directory and regenerate both audit layers.
  3. Remove the old standalone package.
  4. Install only the v3.1 package whose SHA-256 matches the package embedded in the v3.1 overlay.

Source: SKILL.md on GitHub

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

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