Parabolic Short Trade Planner
A three-phase workflow for building Qullamaggie-style parabolic short watchlists with explicit pre-market planning and intraday trigger monitoring. Phase 1 scores S&P 500 stocks on five exhaustion factors using FMP data, Phase 2 generates conditional entry plans with borrow and SSR checks, and Phase 3 walks a finite state machine through live 5-minute bars to detect trigger fires. The design is detection-only: it never sends orders, just emits JSON with concrete share counts when a trigger condition hits. Useful if you trade parabolic exhaustion shorts and want systematic screening plus replay-deterministic monitoring that you can audit before manually pulling the trigger at your broker. The earnings-aware filtering and idempotent state management are thoughtful touches.
- skills.sh installs
- 3.1K
- GitHub stars
- 3.7K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add tradermonty/claude-trading-skills --skill parabolic-short-trade-planner --agent claude-codeInstalls into .claude/skills of the current project.
Files
Overview
Generate Qullamaggie-style Parabolic Short watchlists and conditional pre-market plans for US equities. The skill never sends orders. It emits JSON + Markdown that a human reviews against their broker before entry.
Three phases:
- Phase 1 (
screen_parabolic.py): pulls EOD bars + company profile from FMP, applies hard invalidation rules (mode-aware), scores survivors on 5 factors (weights 30/25/20/15/10), and assigns A/B/C/D grades. - Phase 2 (
generate_pre_market_plan.py): takes the Phase 1 JSON, filters by--tradable-min-grade(defaultB), checks Alpaca short inventory (orManualBrokerAdapter), evaluates SEC Rule 201 SSR state from the inherited prior-day close, and renders three trigger plans per candidate. - Phase 3 (
monitor_intraday_trigger.py): reads the Phase 2 plan, fetches 5-min bars (Alpaca live or fixture), walks each plan's FSM forward by one step, persists per-plan state, and writes anintraday_monitorJSON withstate,entry_actual,stop_actual, andshares_actual(when triggered). One-shot — trader runs it every 1–5 min viawatchor cron; replay-deterministic so re-runs are byte-identical.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/tradermonty/claude-trading-skills
- Categories
- Frontend Development, Rust, CLI & Terminal, Finance & Trading
- First seen
- Jun 3, 2026
