Skip to content
SkillScript-led2,353 tokens in use

Parabolic Short Trade Planner

A three-phase Python toolkit that scores US stocks for parabolic exhaustion, drafts conditional pre-market short plans, and watches 5-minute bars for trigger fires. Detection only, no order routing.

7,428 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/parabolic-short-trade-planner

Skill label

measured from its files

What installing Parabolic Short Trade Planner costs

122tokens idle
2,353tokens in use
13,695tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/_fmp_compat.py, scripts/_market_calendar.py, scripts/adapters/__init__.py, scripts/adapters/alpaca_inventory_adapter.py, scripts/adapters/alpaca_market_data_adapter.py, scripts/adapters/fixture_market_data_adapter.py, scripts/adapters/market_data_adapter.py, scripts/bar_normalizer.py, scripts/broker_short_inventory_adapter.py, scripts/calculators/__init__.py, scripts/calculators/acceleration_calculator.py, scripts/calculators/atr_calculator.py, scripts/calculators/liquidity_metrics_calculator.py, scripts/calculators/ma_extension_calculator.py, scripts/calculators/parabolic_score_calculator.py, scripts/calculators/range_expansion_calculator.py, scripts/check_live_apis.py, scripts/fmp_client.py, scripts/generate_pre_market_plan.py, scripts/intraday_evaluators/__init__.py, scripts/intraday_evaluators/first_red_evaluator.py, scripts/intraday_evaluators/orl_evaluator.py, scripts/intraday_evaluators/vwap_fail_evaluator.py, scripts/intraday_size_resolver.py, scripts/intraday_state_machine.py, scripts/intraday_state_store.py, scripts/invalidation_rules.py, scripts/manual_reasons.py, scripts/market_clock.py, scripts/math_helpers.py, scripts/monitor_intraday_trigger.py, scripts/parabolic_report_generator.py, scripts/parabolic_scorer.py, scripts/plan_builders/__init__.py, scripts/plan_builders/first_red_plan_builder.py, scripts/plan_builders/orl_plan_builder.py, scripts/plan_builders/vwap_fail_plan_builder.py, scripts/screen_parabolic.py, scripts/size_recipe_builder.py, scripts/ssr_state_tracker.py, scripts/state_caps.py, scripts/vwap.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources2/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 63
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/_fmp_compat.py, line 71
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    scripts/adapters/alpaca_inventory_adapter.py, line 50
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/intraday_state_store.py, line 54

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

Parabolic Short Trade Planner follows a Qullamaggie-style parabolic short framework. Phase 1 pulls daily bars and profiles from Financial Modeling Prep and grades stocks on five exhaustion factors. Phase 2 turns the watchlist into per-ticker plans with borrow, SEC Rule 201 short sale restriction and manual-confirmation checks. Phase 3 reads 5-minute bars and reports when a plan’s trigger state changes.

The skill states that it never sends orders. It writes JSON and Markdown files that a person reviews against their broker. It describes screening logic and does not give investment advice.

What You Get

  • A daily watchlist in JSON and Markdown grouped by grade
  • A pre-market plan JSON with three trigger plans per candidate and entry, stop and share formulas
  • Plan status of actionable or watch_only with blocking and advisory manual reasons
  • An intraday monitor JSON with armed, triggered or invalidated state and resolved share counts
  • Earnings-aware checks for upcoming and recent earnings dates

Common Use Cases

  • Building a daily parabolic short watchlist from the S&P 500 or a custom CSV
  • Checking borrow, SSR and manual gating before a plan is considered
  • Running the intraday monitor on a schedule during the first part of the session
  • Testing the whole chain offline with fixtures and no API keys

What Makes It Unique

It covers the whole path from screen to intraday trigger in one skill and keeps the gates visible. Plans separate blocking reasons from advisory ones, manual locate is always flagged, and the monitor is idempotent so a re-run in the same minute produces the same output. Offline modes use fixtures for every phase, and the skill refuses historical live replay because the live universe data is not point-in-time.

Under The Hood

Claude runs Python scripts from the shell. Phase 1 calls the Financial Modeling Prep API with your key for price history, company profiles and the earnings calendar. Phase 2 and Phase 3 can call Alpaca with your Alpaca key and secret to check short inventory and fetch 5-minute market data, and fall back to a manual adapter or fixtures without them. The scripts write report files into an output folder and per-plan state files into a state folder. The skill repeats that it only detects triggers and the trader places any order manually. Dependencies come from a requirements file.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers