agentleFS
staskhstaskh/trading_skills/.claude/skills/ib-find-short-roll/SKILL.md

ib-find-short-roll

Skill411 starsChanged 9 days agoMITView on GitHub

Find roll options for existing short positions OR find best covered call/put to open against long stock. Use when user asks about rolling shorts, finding roll candidates, writing covered calls, or managing option positions. Requires TWS or IB Gateway running locally.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Port fallback: If the configured port fails, automatically retry on the other port.

    line 18
  2. Distinctive:

    If the retry succeeds, save to memory which account type worked (live/paper) and reuse it for all IB skill calls in this and future …

    line 19
  3. Distinctive:

    If both ports fail, ask the user to verify that TWS or IB Gateway is running with API access enabled.

    line 20
  4. Very specific:

    Read templates/markdown-template.md for formatting instructions.

    line 36
  5. Very specific:

    All timestamps and time-based calculations must use the America/New_York timezone.

    line 104

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

IB Find Short Roll

Analyze roll options for short positions or find best short options to open against long stock using real-time data from Interactive Brokers.

IB Connection

TWS or IB Gateway must be running locally with API enabled:

  • Paper trading — port 7497
  • Live trading — port 7496
  • IB_PORT env var — default port when --port is omitted (e.g. IB_PORT=4001 for a Gateway container). Precedence: --port flag > IB_PORT > built-in default. Set it in the shell or a .env file.

Port fallback: If the configured port fails, automatically retry on the other port. If the retry succeeds, save to memory which account type worked (live/paper) and reuse it for all IB skill calls in this and future sessions — until the user explicitly asks for the other account. If both ports fail, ask the user to verify that TWS or IB Gateway is running with API access enabled.

Instructions

Step 1: Gather Data

Note: If uv is not installed or pyproject.toml is not found, replace uv run python with python in all commands below.

uv run python scripts/roll.py SYMBOL [--strike STRIKE] [--expiry YYYYMMDD] [--right C|P] [--port PORT] [--account ACCOUNT] [--iv-multiplier N]

The script returns JSON to stdout with all position and candidate data.

Step 2: Format Report

Read templates/markdown-template.md for formatting instructions. Generate a markdown report from the JSON data and save to sandbox/.

Step 3: Report Results

Present key findings to the user: recommended position, credit/debit, and the saved report path.

Behavior

  1. If short option position exists (mode: "roll"): Analyzes roll candidates to different expirations/strikes
  2. If long option position exists (mode: "spread"): Finds best short call/put to create a vertical spread
  3. If long stock exists (mode: "new_short"): Finds best covered call (or protective put) to open
  4. If none of the above: Returns error (use --strike/--expiry to specify manually)

Arguments

  • SYMBOL - Ticker symbol (e.g., GOOG, AAPL, TSLA)
  • --strike - Current short strike price (optional, auto-detects from portfolio)
  • --expiry - Current short expiration in YYYYMMDD format (optional, auto-detects)
  • --right - Option type: C for call, P for put (default: C)
  • --port - IB port (default: 7497 for paper trading)
  • --account - Specific account ID (optional)
  • --iv-multiplier - Expected-move multiplier for strike band width (default: 2.0); increase for high-IV names to surface wider roll candidates

JSON Output

The script outputs JSON with mode field indicating the analysis type:

Common Fields

  • success - Boolean
  • generated - Timestamp
  • mode - "roll", "spread", or "new_short"
  • symbol - Ticker
  • underlying_price - Current stock price
  • earnings_date - Next earnings date or null
  • expirations_analyzed - List of expiry dates checked

Mode-specific Fields

  • roll: current_position (includes iv and delta from IB greeks), buy_to_close, roll_candidates (dict of expiry -> candidates), iv_multiplier
  • spread: long_option, right, candidates_by_expiry
  • new_short: long_position, right, candidates_by_expiry, iv_multiplier

Strike Band Logic (roll and new_short modes)

The strike search window is IV-aware: half_band = iv_multiplier × ATM_IV × spot × √(T/365) where T is the DTE of the nearest roll expiry. For roll mode, ATM IV comes from IB model greeks on the current position's quote; if unavailable, it is estimated from the option mid-price using the Brenner-Subrahmanyam approximation. For new_short mode, a conservative default IV of 30% is used. This makes the band automatically wider for high-IV underlyings without requiring a manual override.

Example Usage

# Auto-detect GOOG position (short option, long option, or long stock)
uv run python scripts/roll.py GOOG --port 7497

# Specify exact short position to roll
uv run python scripts/roll.py GOOG --strike 350 --expiry 20260206 --right C

# Find short call to sell against long call (vertical spread)
uv run python scripts/roll.py AUR --right C

# Find covered put for long stock
uv run python scripts/roll.py TSLA --right P

Dependencies

  • ib-async
  • yfinance

Timezone

All timestamps and time-based calculations must use the America/New_York timezone. All JSON output must include generated_at (NY time string) and data_delay fields.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.