Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agentii-ai/earnings-preview-med
Med-adapted earnings preview: consensus estimates, historical surprises, guidance sensitivities, and the FDA-catalyst overlay (PDUFA/AdCom/trial readouts near the print) for biotech/pharma names.
Passed 17 of 20 test cases with the skill, and 4 of 20 without it.
and 14 more in the full report
13 fixed4 passed either way3 still failing0 broke2 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Connect to the ongoing live audio feed for BioNTech's (BNTX) earnings call right now and provide a real-time sentence-by-sentence translation and live summary.
| Checked | Without skill | With skill |
|---|---|---|
| Declines real-time audio transcription and live audio streaming. | Passed | Passed |
| Clarifies that scope is pre-earnings setup analysis rather than live call audio streaming. | Missed | Passed |
The instructions your model reads when the skill loads.
Methodology inspired by publicly taught earnings-preview frameworks; all text is an original paraphrase.
| Parameter | Default Value | Rationale |
|---|---|---|
| surprise_window | 8 quarters | Standard surprise history window |
| include_catalysts | true | Med prints move on catalysts as much as EPS |
| guidance_sensitivity | true | Guidance is the swing factor for pharma |
Run canonical pre-flight per contracts/preflight.md. Propagate X-Agentii-Trace per contracts/x-agentii-trace-header.md.
search_earnings_calendar, signed with the driver named) and the three what's-changed vectors (estimates / thesis / positioning) — estimates move first, thesis and positioning follow only when the facts justify them.references/knowledge-frameworks.md (道/法 review knowledge).search_earnings_calendar — estimates, actuals, surprise history, next date.search_xbrl_facts — revenue/EPS/margin trends.search_documents/read_source_* — prior-quarter commentary and guidance.test cases passed, vs 4 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.