Skip to content
SkillScript-led2,943 tokens in use

Earnings Calendar

Pulls the coming week's US earnings announcements from the Financial Modeling Prep API and writes a Markdown report grouped by date and reporting time.

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

Skill label

measured from its files

What installing Earnings Calendar costs

107tokens idle
2,943tokens in use
10,495tokens, 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/fetch_earnings_fmp.py, scripts/fmp_client.py, scripts/generate_report.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
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources11/15

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 36
  • Writes files−8

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

    SKILL.md, line 146
  • Reaches the network−10

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

    scripts/_fmp_compat.py, line 71
  • Reads credentials−15

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

    scripts/fetch_earnings_fmp.py, line 298

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 Calendar retrieves upcoming US earnings announcements from the Financial Modeling Prep (FMP) API. It keeps companies above $2B in market cap and sorts them by date, timing (before open, after close, or not announced) and market cap.

Two Python scripts do the work: one fetches and filters the data, the other renders a Markdown report with EPS and revenue estimates and summary counts. It reports scheduled events and estimates only and gives no investment advice.

What You Get

  • A Markdown report named earnings_calendar_YYYY-MM-DD.md with companies grouped by date and by before-open, after-close or time-not-announced
  • EPS and revenue estimates, market cap, sector and industry for each reporting company
  • A JSON file of the filtered earnings rows that other tooling can read
  • A short chat summary with company counts, the busiest day and the largest names by market cap

Common Use Cases

  • Reviewing which large and mid-cap companies report in the coming week
  • Checking a single day or a single sector’s earnings schedule
  • Building a weekly calendar before reading other market-analysis reports

What Makes It Unique

It is a calendar of scheduled earnings events with a fixed market-cap filter and a set report layout, and scripts produce the report so the format stays the same every week. Timing is normalized to BMO, AMC or TAS, and a manual-entry fallback keeps the report format usable when no key is set. Free FMP keys cover the few calls a weekly report needs.

Under The Hood

The SKILL.md tells the agent to read the FMP API guide, check for an FMP_API_KEY environment variable (or ask for a session key), then run a Python script that makes HTTPS calls to the FMP API for the earnings calendar and company profiles. A second script reads the saved JSON and writes the Markdown report to the working directory. The agent runs shell commands, calls an external web API with your key, and writes files. Reference files in the skill load only when a step needs them.

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