Skip to content
SkillMixed4,098 tokens in use

FinViz Screener

Maps stock screening requests in English or Japanese to FinViz filter codes, builds the screener URL and opens it in Chrome or prints it.

7,427 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/finviz-screener

Skill label

measured from its files

What installing FinViz Screener costs

93tokens idle
4,098tokens in use
29,218tokens, 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 Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/open_finviz_screener.py.

Touches

shelldetectedcredentialsdetected

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
  • Examples15/15
  • Output5/15
  • Size15/15
  • Resources15/15

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 →
Excellent
  • Runs shell commands−5

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

    SKILL.md, line 61
  • Reads credentials−15

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

    scripts/open_finviz_screener.py, line 204

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

FinViz Screener translates requests such as “oversold large caps with high ROE” or “高配当で成長している小型株” into FinViz filter codes, themes and sub-themes. It shows the chosen filters in a table for you to confirm, then builds the screener URL.

A Python script opens the URL in Chrome, with OS-specific fallbacks, or only prints it. The public screener needs no key, and FINVIZ Elite mode is detected from an environment variable. The skill builds a screen from criteria you state and gives no investment advice.

What You Get

  • A FinViz screener URL built from your criteria
  • A confirmation table listing each filter code and its meaning
  • The URL opened in Chrome, or printed when you ask for URL-only output
  • Suggested next steps such as changing the view or sort order

Common Use Cases

  • Describing a screen in everyday words and getting the matching FinViz page
  • Starting from a recipe such as dividend growth or a trend template and refining it
  • Screening by theme and sub-theme, for example AI cloud and compute

What Makes It Unique

It carries a bilingual concept table and a 142-code industry list, supports range tokens such as fa_div_3to8, and validates every filter strictly to prevent URL injection. Theme and sub-theme tokens go through their own arguments. The recipes are written from repeated use and teach an iterative way to tighten or relax a screen.

Under The Hood

The agent reads reference files, then runs a Python script that uses only the standard library to build the URL. It opens the URL in a local Chrome browser or prints it. If the FINVIZ_API_KEY environment variable is set, the script switches to Elite mode, and the screener page itself is fetched by your browser. The agent runs shell commands and may launch a browser. It writes no files.

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