Earnings blackout
Analyst workflows as Claude skills. 62+ tools and 8 workflows spanning earnings, comps, valuation, options flow, factor research, sizing, risk, TCA, and ops. Built in the garage, not the trading floor.
npx -y skills add rgourley/quant-garage --skill earnings-blackoutAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 6 stars6 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
Lightweight watchlist scanner. Takes a comma-separated list of tickers plus a forward window and returns each ticker's earnings status (blackout_imminent, blackout_soon, blackout_extended, just_printed, recent_print, clear, unresolved) with the next/most-recent print date and consensus EPS where available. Use before a trading day to spot which positions are about to print. Earnings-drilldown is the deep dive; this is the batch scan.
SKILL.md
3.7 KB, as published. Nobody here has run it
earnings-blackout
You have a watchlist of 20 names. Which print this week? Which printed yesterday and might gap on follow-up news? Which are clear to trade without earnings-event risk? Run the scanner. One pass per ticker over Benzinga (or SEC EDGAR as fallback), one classification per ticker, one grouped exception report at the end.
This is the pre-trade hygiene check, not a full preview. For a single
name's full sell-side preview (implied move, beat/miss history, peer
reaction, drift), use earnings-drilldown.
For the per-event windowing study, use event-study.
When to invoke
- Morning watchlist scan before the market opens
- Position-sizing check: which names in the book have earnings risk in the next N days
- Post-mortem: which name in the watchlist already printed and might have residual gap risk
What you need
- A watchlist (
--watchlist NVDA,TSLA,AMZN,GOOGL,META,AAPL,MSFT) MASSIVE_API_KEYexported in the environment- Optional: Benzinga earnings add-on for forward dates + consensus EPS (Tier A). Without it, the skill falls back to SEC EDGAR 8-K filings (Tier B, past-only).
Quick start
python3 examples/run-earnings-blackout.py \
--watchlist NVDA,TSLA,AMZN,GOOGL,META,AAPL,MSFT \
--window-days 7
Status buckets
Seven, returned in results[].status:
blackout_imminent— earnings 0-3 days forward. Position-sizing decisions need to be locked in NOW.blackout_soon— earnings 4-7 days forward. Watching for IV ramp, positioning unwind.blackout_extended— earnings 8+ days forward. Only surfaces when--window-days > 7.just_printed— earnings 0-3 days past. Watch for analyst-day follow-on, guidance digestion, gap fill.recent_print— earnings 4-7 days past. Less relevant, ranked low in render.clear— no earnings in either the forward or past window.unresolved— the resolver returned nothing from Benzinga AND the SEC EDGAR fallback. Could mean the ticker has no 8-K with items 2.02 / 7.01 / 8.01 in the window, or that the CIK lookup failed. Surfaced explicitly rather than silently dropped.
Tiers
- Tier A (Benzinga): True forward calendar dates, consensus EPS, consensus revenue, expected release time (BMO/AMC/DMH).
- Tier B (SEC EDGAR only): Past prints only. No forward calendar
(EDGAR is filing-based). No consensus EPS. Surfaces
item_codeandsignal_strength(strong=2.02, soft=7.01/8.01) so consumers can weight conservatively.
The skill returns tier: "A" if any ticker resolved via Benzinga.
tier_caveats[] lists what the user is missing.
Output
Always emits canonical JSON matching
output-schema.json and a rendered exception
report grouped by status (imminent first). See
references/rendering.md for the rules
and references/methodology.md for the
two-tier resolver chain.
Reading
references/methodology.md— Benzinga primary, SEC EDGAR 8-K fallback, item-code interpretation, CIK chainreferences/rendering.md— exception- report grouping rules