Skip to content
SkillScript-led1,533 tokens in use

Uptrend Analyzer

Scores US market breadth from 0 to 100 using a free public uptrend-ratio CSV covering about 2,800 stocks in 11 sectors, with a sector heatmap and exposure guidance.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/uptrend-analyzer

Skill label

measured from its files

What installing Uptrend Analyzer costs

77tokens idle
1,533tokens in use
4,979tokens, 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/calculators/__init__.py, scripts/calculators/historical_context_calculator.py, scripts/calculators/market_breadth_calculator.py, scripts/calculators/momentum_calculator.py, scripts/calculators/sector_participation_calculator.py, scripts/calculators/sector_rotation_calculator.py, scripts/data_fetcher.py, scripts/provenance_contract.py, scripts/report_generator.py, scripts/scorer.py, scripts/uptrend_analyzer.py.

Touches

shelldetectedwrites filesdetected

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 →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples6/15
  • Output5/15
  • Size15/15
  • Resources1/15

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 55
  • Writes files−8

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

    scripts/report_generator.py, line 15

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

Uptrend Analyzer diagnoses how broad a market advance is. It downloads Monty’s Uptrend Ratio Dashboard CSV from GitHub and computes a composite score from five components: overall breadth, sector participation, sector rotation, momentum and historical context.

The score maps to zones from Strong Bull to Bear with matching exposure guidance, and warning rules for late cycle, high spread and divergence can tighten it. Output is a JSON file and a Markdown report. It needs no API key and describes market conditions without giving investment advice.

What You Get

  • A composite score from 0 to 100 with a zone from Strong Bull to Bear
  • Exposure guidance bands from full to capital preservation
  • A sector heatmap showing the strongest and weakest sectors, plus rotation and momentum signals
  • JSON and Markdown reports with a historical confidence level and provenance fields

Common Use Cases

  • Checking whether a rally is broad or narrow
  • Reading the daily breadth picture without a paid data subscription
  • Feeding a breadth score into an exposure summary with the other market regime skills

What Makes It Unique

It runs on a free public CSV, so it works with no API key, and its score direction is the reverse of the market top detector: higher is healthier. Warning penalties for late-cycle commodity leadership, wide sector spreads and divergence tighten the guidance even when the headline score is high.

Under The Hood

The agent runs one Python script from the shell. The script downloads CSV data from a public GitHub repository over the internet using the requests library, calculates the five component scores and writes JSON and Markdown reports to disk. No API key is used. A run ID flag can be passed so that the output carries data provenance fields for the exposure summary skill. A methodology reference file explains the scoring and sector groups.

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