Skip to content
SkillScript-led5,432 tokens in use

Theme Detector

Detects and ranks trending market themes across sectors from FINVIZ industry data, scoring heat, lifecycle maturity and confidence for bullish and bearish themes.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/theme-detector

Skill label

measured from its files

What installing Theme Detector costs

52tokens idle
5,432tokens in use
20,683tokens, 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/_market_calendar.py, scripts/calculators/__init__.py, scripts/calculators/heat_calculator.py, scripts/calculators/industry_ranker.py, scripts/calculators/lifecycle_calculator.py, scripts/calculators/theme_classifier.py, scripts/calculators/theme_discoverer.py, scripts/config_loader.py, scripts/default_theme_config.py, scripts/etf_scanner.py, scripts/finviz_performance_client.py, scripts/leadership.py, scripts/report_generator.py, scripts/representative_stock_selector.py, scripts/scorer.py, scripts/tests/conftest.py, scripts/tests/test_config_loader.py, scripts/tests/test_credential_diagnostics.py, scripts/tests/test_detect_divergence.py, scripts/tests/test_elite_volume_ranking.py, scripts/tests/test_etf_scanner.py, scripts/tests/test_finviz_elite_export_contract.py, scripts/tests/test_finviz_group_export.py, scripts/tests/test_finviz_performance_client.py, scripts/tests/test_fmp_stable_migration.py, scripts/tests/test_heat_calculator.py, scripts/tests/test_industry_ranker.py, scripts/tests/test_leadership.py, scripts/tests/test_lifecycle_calculator.py, scripts/tests/test_market_calendar_contract.py, scripts/tests/test_missing_calendar_dependency_exit.py, scripts/tests/test_missing_dependency_exit.py, scripts/tests/test_report_generator.py, scripts/tests/test_representative_stock_selector.py, scripts/tests/test_scorer.py, scripts/tests/test_theme_classifier.py, scripts/tests/test_theme_detector_e2e.py, scripts/tests/test_theme_discoverer.py, scripts/tests/test_theme_history.py, scripts/tests/test_theme_matcher.py, scripts/tests/test_uptrend_client.py, scripts/theme_detector.py, scripts/theme_history.py, scripts/theme_matcher.py, scripts/uptrend_client.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
  • Structure22/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • 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 →
Fair
  • Reaches the network−10

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

    SKILL.md, line 73
  • Runs shell commands−5

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

    SKILL.md, line 73
  • Reads credentials−15

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

    SKILL.md, line 78
  • Writes files−8

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

    scripts/report_generator.py, line 367
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/tests/test_finviz_elite_export_contract.py, line 98

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

Theme Detector finds which market themes are moving, such as AI or clean energy, by combining momentum, volume, uptrend ratio and breadth across industries. Each theme gets a heat score from 0 to 100, a lifecycle stage from Emerging to Exhausting, and a confidence level.

It runs a Python orchestrator against FINVIZ, in Elite mode with a key or by scraping public pages, and can add FMP valuation data, daily stock scan hits and a history file. A web search step then checks the narrative for the top themes. The output describes market conditions and is not investment advice.

What You Get

  • A ranked list of bullish and bearish themes with heat scores and lifecycle stage
  • A confidence rating per theme, capped at medium from data alone and raised only by narrative confirmation
  • Representative stocks and leader candidates for each theme with the evidence behind them
  • Theme history and acceleration metrics when you pass a history file

Common Use Cases

  • Asking which themes are hot or cold this week before planning research
  • Spotting crowded late-stage themes against emerging ones
  • Checking whether a theme such as defense or clean energy still has momentum

What Makes It Unique

It scores three separate things, heat, lifecycle maturity and confidence, so a strong but exhausted theme reads differently from an early one. Bearish themes are scored the same way as bullish ones, and optional stock-leadership and basket-match evidence show how specific each theme match is.

Under The Hood

The skill runs a Python script from the shell. The script fetches industry and stock data from FINVIZ, either through the Elite export with an API key or by scraping public pages at a slow rate, and can call the Financial Modeling Prep API for valuation data when a key is set. It also uses market data libraries for price history. Reports are written as files in a reports folder. After the script finishes, the agent uses web search to confirm the narrative for the top themes. API keys are read from environment variables or command flags.

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