Earnings watch
Skill OneWave-AI/open-agent-stack/plugins/market-desk/skills/earnings-watch
Open-source plugins, managed agents, multi-agent orchestrators, and design tokens for Claude Code, the Agent SDK, and any AI tool. By OneWave AI.
npx -y skills add OneWave-AI/open-agent-stack --skill earnings-watchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Earnings-season prep for your holdings and watchlist -- report dates, what the market is actually watching per name, prior-quarter context, and a post-report debrief template. Preparation, not prediction. Use in the weeks around earnings season.
SKILL.md
2.2 KB, as published. Nobody here has run it
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.