Skip to content
SkillScript-led3,931 tokens in use

CANSLIM Screener

Scores US stocks on all seven CANSLIM components with Financial Modeling Prep data and a Finviz fallback, then ranks them in JSON and Markdown reports.

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

Skill label

measured from its files

What installing CANSLIM Screener costs

60tokens idle
3,931tokens in use
30,673tokens, 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/calculators/earnings_calculator.py, scripts/calculators/growth_calculator.py, scripts/calculators/institutional_calculator.py, scripts/calculators/leadership_calculator.py, scripts/calculators/market_calculator.py, scripts/calculators/new_highs_calculator.py, scripts/calculators/supply_demand_calculator.py, scripts/check_institutional_endpoint.py, scripts/finviz_stock_client.py, scripts/fmp_client.py, scripts/report_generator.py, scripts/scorer.py, scripts/screen_canslim.py, scripts/tests/conftest.py, scripts/tests/test_canslim_calculators_coverage.py, scripts/tests/test_canslim_coverage.py, scripts/tests/test_canslim_fixes.py, scripts/tests/test_credential_diagnostics.py, scripts/tests/test_fmp_fallback.py, scripts/tests/test_fmp_stable_migration.py, scripts/tests/test_institutional_fallback.py, scripts/tests/test_leadership_price_gaps.py, scripts/tests/test_leadership_rs.py, scripts/tests/test_missing_dependency_hint.py, scripts/tests/test_price_bars_contract.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
  • Structure23/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources14/15

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 →
Good
  • Reaches the network−10

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

    SKILL.md, line 70
  • Runs shell commands−5

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

    SKILL.md, line 70
  • Reads credentials−15

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

    SKILL.md, line 122
  • Writes files−8

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

    scripts/report_generator.py, line 27

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

CANSLIM Screener applies William O’Neil’s growth stock method to a list of US stocks. A Python script pulls quote, earnings, price history and institutional data from the Financial Modeling Prep API, scores the seven components (current earnings, annual growth, new highs, supply and demand, leadership, institutional sponsorship and market direction) and combines them into a 0 to 100 composite.

When institutional ownership data is missing from FMP, the script scrapes the figure from Finviz. Reports list the market condition first and then the top candidates with a breakdown per component. The output is a screening aid and not investment advice.

What You Get

  • A ranked list of stocks with composite scores and rating bands from Above Average to Exceptional+
  • A breakdown of each component per stock, including multi-period relative strength
  • A market condition summary that flags a bear market through the M component
  • A JSON file for other tools and a Markdown report, both timestamped

Common Use Cases

  • Screening a custom list of tickers against O’Neil’s growth criteria
  • Checking which large caps rank highest on earnings growth and relative strength
  • Using a different relative strength benchmark than the S&P 500
  • Running a faster pass with the relative strength component disabled

What Makes It Unique

It covers all seven CANSLIM components, not a subset, and handles incomplete data openly: stocks with missing or invalid price closes for the relative strength calculation are marked unavailable and left out of the ranking, with dated data gaps in the report. The API budget is spelled out (about 7 FMP calls per stock plus 3 for market data), so a free-tier user can size a run with the max-candidates flag.

Under The Hood

The agent runs a Python script that calls the Financial Modeling Prep API over the network with the user’s API key (set in the FMP_API_KEY environment variable or passed on the command line). It also scrapes Finviz web pages for institutional ownership when FMP data is incomplete, with a short pause between requests. The skill asks the user to install requests, beautifulsoup4 and lxml with pip. It writes a JSON file and a Markdown report into an output folder, and the agent runs shell commands to find and read them.

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