Preflight trade
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 preflight-tradeAssembled 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
Before-you-execute sanity check on a single ticker + intended action (buy, sell, add, reduce, exit). Composes technical-briefing + earnings-blackout (14d) + news-scanner (last N) + corporate-actions-scanner (90d) into a verdict (go, wait, review) plus red/green flag lists. Use when the operator is about to execute a trade and wants a fast honest read on whether now is a bad time.
SKILL.md
1.9 KB, 417 tokens by cl100k_base, as published. Nobody here has run it
preflight-trade
Single-ticker preflight check. You hand over ticker + action, get back a verdict (go, wait, review) plus red/green flags derived from four sub-skills.
Not a recommendation to trade or not trade. A structured "is now obviously a bad time" gate. If the tool says WAIT, the flags explain why. If GO, the flags list what's supporting.
When to invoke
- Before hitting buy/sell/reduce on a specific name
- "Preflight NVDA buy", "should I trim ALLO", "any red flags on X"
- Fills the "is now a bad moment" moment
Actions supported
buy, sell, add, reduce, exit. The action tilts the verdict
threshold: buy and add require fewer red flags to warrant WAIT
than sell or exit (bias toward defense on entry).
Verdict logic
- GO: 2+ green flags AND <=1 red flag
- WAIT: 3+ red flags AND <=1 green flag, OR (buy/add + 2+ reds)
- REVIEW: everything else (mixed signals, human judgment needed)
What you get back
Layer 1 JSON matching output-schema.json.
Verdict, red/green flag arrays, four sub-skill payloads.
Layer 2 rendered note. Verdict block on top, flags, then each
sub-skill's own render below. See
references/rendering.md.
How it works
Runs 4 sub-skills for the ticker, then applies deterministic rules
in _build_verdict():
- technical-briefing: trend regime, RSI, ATR
- earnings-blackout: pending print
- news-scanner: recent sentiment tilt
- corporate-actions-scanner: material 8-K in the last 90d
What ships with it: 4 files
3.6 KB alongside SKILL.md
references/
- rendering.md763 B
- output-schema.json1.2 KB
- README.md974 B
- requires.yml763 B