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.