Skip to content
SkillScript-led4,649 tokens in use

Breadth Chart Analyst

Reads S&P 500 breadth and uptrend stock ratio data from public CSV files, optionally checks chart images, and writes a Markdown breadth report.

7,426 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/breadth-chart-analyst

Skill label

measured from its files

What installing Breadth Chart Analyst costs

108tokens idle
4,649tokens in use
18,049tokens, 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/detect_breadth_values.py, scripts/detect_uptrend_ratio.py, scripts/extract_chart_right_edge.py, scripts/fetch_breadth_csv.py.

Touches

shelldetectednetworkdetected

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
  • Output15/15
  • Size15/15
  • Resources10/15

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 96
  • Reaches the network−10

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

    scripts/fetch_breadth_csv.py, line 19

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

Breadth Chart Analyst looks at two market breadth measures: the S&P 500 Breadth Index based on the 200-day moving average, and the US Stock Market Uptrend Stock Ratio. It takes the exact numbers from public CSV files and uses chart images only as visual context.

The agent follows a fixed workflow that fetches the CSV values, classifies each reading, checks the latest data points for trend direction, builds scenarios, and saves a report in the reports folder. The output describes market conditions and is not investment advice.

What You Get

  • Current 200-day MA, 8-day MA and uptrend ratio readings with a class for each
  • A dead cross check (8-day MA below 200-day MA) and the size of the gap
  • Per-sector uptrend ratios with overbought and oversold flags
  • A Markdown report with scenarios and notes for different kinds of traders, named by chart type and date

Common Use Cases

  • Getting a breadth reading without any chart image
  • Checking a screenshot of a breadth chart against the data behind it
  • Writing a weekly market breadth summary
  • Telling apart a developing signal from a failed reversal

What Makes It Unique

The CSV values are the primary source and chart images are supplementary, because image detection broke when chart formats changed. A two-stage review covers the full chart for history and then the rightmost quarter for current values, which prevents old readings being taken as current ones. The agent must verify line colours and the latest three to five data points before it states a trend.

Under The Hood

The agent runs a Python script that downloads three public CSV files over the network (a market breadth file on GitHub Pages and two uptrend dashboard files on raw.githubusercontent.com) using the standard library, then prints the readings. When chart images are supplied it can run a second script that crops the right edge of the image; older OpenCV detection scripts exist but are marked deprecated. The agent reads Markdown reference files and a template, and then writes a report file into the reports folder. No API key is needed.

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