Skip to content
SkillScript-led2,838 tokens in use

Value Dividend Screener

Screens US stocks for a 3% or higher yield, P/E under 20 and P/B under 2, then ranks them on three-year dividend, revenue and EPS growth, sustainability and quality.

7,432 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/value-dividend-screener

Skill label

measured from its files

What installing Value Dividend Screener costs

102tokens idle
2,838tokens in use
10,233tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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/_price_bars.py, scripts/fmp_client.py, scripts/screen_dividend_stocks.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
  • Frontmatter12/15
  • Structure25/25
  • Examples9/15
  • 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
  • Reads credentials−15

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

    SKILL.md, line 54
  • Runs shell commands−5

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

    SKILL.md, line 60
  • Reaches the network−10

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

    SKILL.md, line 233
  • 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 49
  • Writes files−8

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

    scripts/screen_dividend_stocks.py, line 1504

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

Value Dividend Screener finds dividend stocks that combine value, income and growth. A two-stage mode pre-filters the market with the FINVIZ Elite export, then runs detailed analysis through the Financial Modeling Prep API. An FMP-only mode starts from the FMP stock screener but uses many more API calls.

For each candidate it computes three-year dividend, revenue and EPS growth, payout and free cash flow coverage, debt and liquidity ratios, ROE and margins, and ranks stocks by a composite score. The script writes a JSON file and the agent turns it into a Markdown report. It is a screening tool and not investment advice.

What You Get

  • A ranked JSON list of the top stocks, 20 by default, with valuation, growth, sustainability, financial health and quality fields
  • A Markdown report built from a template with the metrics for each stock
  • Methodology notes that explain the filters, the scoring and the limits of the screen
  • Answers to follow-up questions from bundled reference guides

Common Use Cases

  • Looking for income stocks at reasonable valuations with growing dividends
  • Telling a sustainable payout from a possible dividend trap using cash flow coverage
  • Cutting API usage by pre-filtering with FINVIZ before detailed analysis

What Makes It Unique

Two-stage screening can reduce FMP calls by roughly 90 percent. The sustainability fields keep observed cash flow shortfalls, zero coverage and missing data as separate states, and the report copies the stored note without adding claims. Reference guides cover advanced customization such as sector screens and CSV export.

Under The Hood

The agent runs a Python script from the shell. It needs an FMP API key and optionally a FINVIZ Elite key, read from environment variables or command flags. The script downloads data from the FINVIZ export and the FMP API through a bundled client that masks keys in errors and retries once on rate limits, and it writes the results to a JSON file. The agent reads that file and writes the report. Both services are third-party and the FINVIZ Elite one is a paid subscription.

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