Skip to content
SkillScript-led1,949 tokens in use

Exposure Coach

Combines market breadth, uptrend, regime, top-risk and institutional-flow reports into a one-page market posture with an exposure ceiling and a recommendation label.

7,427 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/exposure-coach

Skill label

measured from its files

What installing Exposure Coach costs

49tokens idle
1,949tokens in use
4,605tokens, 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/calculate_exposure.py, scripts/evaluation_coverage.py, scripts/provenance_contract.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 →
Excellent
  • Frontmatter8/15
  • Structure23/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources7/15

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 49
  • Writes files−8

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

    scripts/calculate_exposure.py, line 827

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

Exposure Coach reads the JSON outputs of other market-analysis skills (market breadth, uptrend, macro regime, market top, follow-through day, themes, sectors and institutional flow) and scores them into one posture summary.

The summary has an equity exposure ceiling from 0 to 100 percent, a growth or value bias, a participation reading, a label of NEW_ENTRY_ALLOWED, REDUCE_ONLY or CASH_PRIORITY, and a confidence level based on how many inputs were present. It is an analytical summary of those reports and not investment advice.

What You Get

  • A JSON report with the exposure ceiling, bias, participation, recommendation, confidence and component scores
  • A one-page Markdown market posture summary with a rationale
  • Lists of provided, missing and unparseable inputs, with warnings
  • Timestamped files named exposure_posture_YYYY-MM-DD_HHMMSS in the reports folder

Common Use Cases

  • Reading one posture summary at the start of a trading week
  • Reconciling conflicting breadth, regime and flow reports
  • Re-assessing the posture after a major macro or market event

What Makes It Unique

It is the integration layer for the market-regime skills, and it fails safe: incomplete inputs lower the ceiling and confidence, and invalid upstream reports are excluded without manual repair. Confidence describes input completeness only, and the skill states that it says nothing about freshness, verified quality or prediction accuracy.

Under The Hood

The agent runs a local Python script that reads JSON reports produced by other skills and writes JSON and Markdown posture reports into the reports folder. The prerequisites list an FMP_API_KEY environment variable for the institutional-flow data, so the upstream flow skill reaches a web API. The agent runs shell commands and writes files. Reference files with the scoring rules and the regime-to-ceiling map load when 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