Skip to content
SkillScript-led1,658 tokens in use

Earnings Trade Analyzer

Scores recent post-earnings stocks from 0 to 100 on five factors and grades them A to D, using Financial Modeling Prep data and writing JSON and Markdown reports.

7,426 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/earnings-trade-analyzer

Skill label

measured from its files

What installing Earnings Trade Analyzer costs

83tokens idle
1,658tokens in use
2,743tokens, 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/_fmp_compat.py, scripts/_market_calendar.py, scripts/analyze_earnings_trades.py, scripts/calculators/__init__.py, scripts/calculators/gap_size_calculator.py, scripts/calculators/ma200_calculator.py, scripts/calculators/ma50_calculator.py, scripts/calculators/pre_earnings_trend_calculator.py, scripts/calculators/volume_trend_calculator.py, scripts/fmp_client.py, scripts/report_generator.py, scripts/scorer.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
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources2/15

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 →
Good
  • Runs shell commands−5

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

    SKILL.md, line 31
  • Reads credentials−15

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

    SKILL.md, line 70
  • Reaches the network−10

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

    SKILL.md, line 70
  • Writes files−8

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

    scripts/analyze_earnings_trades.py, line 652

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

Earnings Trade Analyzer looks at companies that reported earnings in a recent window and scores each reaction with a five-factor system: gap size, pre-earnings trend, volume trend, position against the 200-day average and position against the 50-day average. Each stock gets a 0 to 100 score and an A to D grade.

A Python script pulls the data from the Financial Modeling Prep (FMP) API and writes a JSON file and a Markdown table. The output describes how past earnings reactions scored. It is not investment advice.

What You Get

  • A JSON report with schema version 1.0 and a Markdown report, both timestamped, listing scored candidates
  • A composite score from 0 to 100 and an A, B, C or D grade for each stock
  • A breakdown of the five components, with the strongest and weakest named for each stock
  • Counts of rows with unknown reporting timing, so the gap assumption stays visible

Common Use Cases

  • Ranking the past few days of earnings reactions by a fixed scoring method
  • Comparing gap size, volume and trend position across many reporters in one table
  • Re-running a past date with an as-of setting to reproduce a report

What Makes It Unique

The scoring is computed by scripts with fixed weights and grade bands, so the same inputs give the same grades. The skill documents what to do when the earnings calendar comes back empty on a trading day: it exits with a named reason code and labels any fallback result as preliminary and ungraded. It also uses an exchange calendar to tell a quiet weekend from a data outage.

Under The Hood

The agent runs a Python script that calls the FMP API over HTTPS with your FMP_API_KEY (environment variable or argument) and counts its calls against a budget. It uses a market-calendar package to check trading sessions. The script writes JSON and Markdown reports into the output directory. The fallback path in SKILL.md has the agent run a curl command against the FMP earnings endpoint and per-symbol quote calls. Scoring rules live in a reference file the agent reads.

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