Skip to content
SkillScript-led3,798 tokens in use

Dividend Growth Pullback Screener

Finds US dividend growth stocks with 12 percent or higher dividend growth whose 14-day RSI has dropped to 40 or lower, using FMP data and an optional FINVIZ Elite pre-screen.

7,426 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/dividend-growth-pullback-screener

Skill label

measured from its files

What installing Dividend Growth Pullback Screener costs

80tokens idle
3,798tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/fmp_client.py, scripts/screen_dividend_growth_rsi.py, scripts/tests/test_credential_diagnostics.py, scripts/tests/test_finviz_export_contract.py, scripts/tests/test_fmp_stable.py, scripts/tests/test_screen_dividend_growth_rsi.py, scripts/tests/test_screening_flow.py, scripts/tests/test_shared_fmp_transport.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure22/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • Resources13/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Needs attention
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 45
  • Writes to a key folder or startup file−25

    writes to a key folder or a shell startup file

    references/fmp_api_guide.md, line 66
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/fmp_client.py, line 32
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    scripts/fmp_client.py, line 156
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/screen_dividend_growth_rsi.py, line 1287
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/tests/test_finviz_export_contract.py, line 70

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

Dividend Growth Pullback Screener combines a fundamental dividend screen with a technical filter. A Python script checks yield, market cap, three-year dividend growth, payout sustainability and financial health through the Financial Modeling Prep API, then calculates a 14-period RSI from daily closes and keeps stocks at or below 40.

An optional two-stage mode uses a FINVIZ Elite pre-screen to shrink the candidate list before the detailed FMP analysis. Results are ranked by a composite score and saved as JSON and Markdown. The output is a screening aid and not investment advice.

What You Get

  • A ranked list of stocks that meet the dividend growth, yield and RSI criteria
  • Per stock: current yield, three-year dividend growth, payout and free cash flow coverage, RSI value and zone
  • A composite score weighting dividend growth, financial quality, technical setup and valuation
  • A JSON results file and a Markdown screening report

Common Use Cases

  • Looking for dividend growers during a market pullback
  • Narrowing a large universe with a FINVIZ pre-screen before spending FMP calls
  • Relaxing the RSI or growth thresholds when no stock qualifies
  • Pairing with market breadth and news skills to confirm a broad pullback

What Makes It Unique

It joins two filters that screeners usually keep apart: strong dividend compounding and short-term oversold timing. The sustainability test is strict: free cash flow must exceed dividends paid for non-REITs, missing cash flow data never confirms sustainability, and REITs are judged on a simplified funds-from-operations payout. The report groups entries by RSI zone (extreme oversold, strong oversold, early pullback).

Under The Hood

The agent runs a Python script that calls the Financial Modeling Prep API over the network with the user’s key, and when requested calls the FINVIZ Elite API with a second key. Both keys come from environment variables or command line options. It uses a bundled client that masks keys in output, retries once on malformed JSON, and waits and retries once on a rate limit. The script writes JSON and Markdown files; depending on the build they land in the working directory or a logs folder, so the agent should check the printed paths. The bundled FMP reference guide also shows an optional shell command that appends the API key to a shell startup file such as .bashrc; the agent only does this if the user asks for a persistent key. Free FMP plans may not include the screener endpoint, and the skill says so.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers