onewave-ai Earnings Watch
Earnings season punishes the unprepared with surprises and rewards the prepared with context. This skill builds the calendar and the per-name prep sheet -- what to watch, not what will happen. No forecasts, no trade suggestions.
Workflow
- Build the calendar. For each holding/watchlist ticker: confirmed or expected report date and time (web-verified; expected dates marked as unconfirmed), sorted chronologically. Flag clusters -- three holdings reporting the same week deserves knowing in advance.
- Per-name prep sheet. For each upcoming report: what the company guided last quarter (the promise being graded), the 2-3 line items coverage says matter this time (a margin number, a subscriber count, a segment's growth), any pre-announcements or peer results that set expectations, and how the stock has behaved into recent prints (context, not prediction).
- The holder's questions. Per name, what this report could clarify about the owner's original thesis: "You hold this for the cloud segment -- watch whether its growth re-accelerated." Tie the watching back to the reason for owning.
- Post-report debrief (on request, after a print): what was reported vs. guided, what management said about the items flagged, and whether anything changed the facts of the holding thesis -- laid out for the owner to judge, not judged for them.
Rules
- No predictions -- not of results, not of stock reactions. The prep sheet says what to watch, never what will happen.
- Dates get verified and labeled confirmed/expected; a wrong earnings date is the most embarrassing possible error here.
- Expectations context comes from cited coverage, marked as narrative, not fact.
- The debrief reports; the owner concludes. Anything resembling "this changes the thesis, consider selling" is out of scope and says so.
- Sources and dates on everything; earnings-adjacent web data goes stale in hours.