agentleFS
staskhstaskh/trading_skills/.claude/skills/ib-pmcc-advisor/SKILL.md

ib-pmcc-advisor

Skill411 starsChanged 8 days agoMITView on GitHub

Analyze PMCC (Poor Man's Covered Call / diagonal spread) positions from IB portfolio. For each diagonal spread, reports short leg risk (delta, IV, assignment probability), daily P&L projections, top-3 roll candidates, and a side-by-side comparison table. 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 .claude/skills/ib-pmcc-advisor/templates/markdown-template.md for full formatting instructions.

    line 46
  5. Very specific:

    All logic lives in src/trading_skills/broker/pmcc_advisor.py:

    line 172

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 PMCC Advisor

Analyzes all PMCC (diagonal call spread) positions in the IB portfolio and provides actionable advice on the short leg: assignment risk, P&L projections per day, and ranked roll recommendations.

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: Run the script

uv run python .claude/skills/ib-pmcc-advisor/scripts/pmcc_advisor.py [--port PORT] [--account ACCOUNT] [--min-roll-dte N] [--price-mode mid|last]

The script returns JSON to stdout. Parse it and use it for the response below.

Step 2: Default response — brief inline summary

Unless the user explicitly asks for a report or JSON output, respond with a concise inline summary only. No files saved.

Format:

  • One line per spread: SYMBOL — short $STRIKE exp DATE (δ=X, assign=Y%) — [HOLD / ROLL to $STRIKE]
  • Lead with any red flags (assignment > 40%, DTE < 7, earnings within short window).
  • For flagged spreads, add one extra line with the top roll candidate and net credit.
  • Clean positions: the one-line summary is enough.

Step 3: Generate files only when explicitly requested

MD report — triggered by: "save a report", "generate a report", "write a report", "markdown", "PDF".

Read .claude/skills/ib-pmcc-advisor/templates/markdown-template.md for full formatting instructions. Save to sandbox/pmcc_advisor_{ACCOUNT}_{YYYY-MM-DD}_{HHmm}.md. Use first account ID; derive timestamp from generated_at.

The report must include all sections per spread:

  1. Red flags summary — assignment > 40%, DTE < 7, no rolls, earnings warnings
  2. Company description — one sentence from your own knowledge (always)
  3. Technical profile — RSI, MACD, EMA crossover, ADX, SMA distance, 3mo return, bullish score (only if technical data is present in conversation context; omit otherwise)
  4. Spread structure table — both legs: strike, expiry, DTE, cost, current price, IV
  5. Short leg risk — delta (BS + IB), assignment probability with risk label
  6. Daily P&L projections — all rows: date, days to expiry, best exit spot, max P&L (mark peak row)
  7. Roll candidates table — strike, expiry, DTE, delta, assign%, IV, net credit, $/day, P&L if assigned, bid/ask
  8. Comparison table — current vs roll_1/2/3 side by side
  9. Recommendation — hold/roll/close with reasoning

JSON output — triggered by: "save JSON", "export JSON", "save the data", "output file".

Save raw script output to sandbox/pmcc_advisor_{ACCOUNT}_{YYYY-MM-DD}_{HHmm}.json.

Arguments

FlagDefaultDescription
--port7497IB Gateway/TWS port
--accountallSpecific account ID
--min-roll-dte7Minimum DTE for roll candidates
--price-modemidOption price: mid (bid+ask)/2 or last
--symbolsallAnalyze only these symbols (e.g. --symbols NVDA WMT)

JSON Output Structure

{
  "generated_at": "2026-04-30 10:25 ET",
  "data_delay": "real-time",
  "accounts": ["Uxxxxxxxx"],
  "price_mode": "mid",
  "min_roll_dte": 7,
  "symbols_filter": ["NVDA", "WMT"],
  "spreads": [
    {
      "symbol": "NVDA",
      "account": "Uxxxxxxxx",
      "qty": 10,
      "underlying_price": 201.46,
      "leaps_expiry": "20260918",
      "earnings": {
        "date": "2026-05-20",
        "timing": "AMC",
        "warning_short": false,
        "warning_roll_indices": [1, 2, 3]
      },
      "long": {
        "strike": 180.0, "expiry": "20260918", "dte": 141,
        "avg_cost": 35.51, "current_price": 36.20,
        "iv_pct": 42.1, "ib_delta": 0.7821, "ib_iv_pct": 41.8
      },
      "short": {
        "strike": 210.0, "expiry": "20260618", "dte": 49,
        "premium_received": 6.88, "current_price": 5.10,
        "iv_pct": 38.5, "delta": 0.3421, "assignment_prob_pct": 28.4,
        "ib_delta": 0.3415, "ib_iv_pct": 38.2
      },
      "daily_pnl": [
        {"date": "2026-04-30", "days_to_short_expiry": 49.0, "optimal_spot": 215.20, "pnl": 1234.56},
        {"date": "2026-05-01", "days_to_short_expiry": 48.0, "optimal_spot": 214.80, "pnl": 1289.10}
      ],
      "roll_candidates": [
        {
          "strike": 215.0, "expiry": "20260717", "dte": 78,
          "price": 5.80, "delta": 0.2910, "assignment_prob": 22.5,
          "iv_pct": 37.2, "net_credit": 0.70, "profit_per_day": 0.0744,
          "pnl_if_assigned": 3580.0, "bid": 5.60, "ask": 6.00
        }
      ],
      "comparison": {
        "current":  {"strike": 210, "expiry": "20260618", "dte": 49, "delta": 0.3421, "assignment_prob": 28.4, "profit_per_day": 0.1404, "pnl_if_assigned": 1880.0},
        "roll_1":   {"strike": 215, "expiry": "20260717", "dte": 78, "delta": 0.2910, "assignment_prob": 22.5, "profit_per_day": 0.0744, "pnl_if_assigned": 3580.0}
      }
    }
  ]
}

Key Fields

  • symbols_filter — list of uppercase symbols when --symbols was used; null means full portfolio
  • data_delay — "real-time" if live quotes available, "stalled - using last price" if IBKR quotes unavailable
  • generated_at — NY timezone timestamp
  • leaps_expiry — expiry of the long leg (YYYYMMDD); all roll candidates are capped at or before this date
  • earnings.date — next earnings date (YYYY-MM-DD) from Yahoo Finance; null for ETFs
  • earnings.timing — "BMO" (before open) or "AMC" (after close)
  • earnings.warning_short — true if earnings fall within the last 7 calendar days before short expiry
  • earnings.warning_roll_indices — 1-based indices of roll candidates whose expiry window contains the earnings date
  • delta / ib_delta — BS-calculated vs. IBKR model Greeks (both reported when available)
  • iv_pct / ib_iv_pct — IV in percent; BS-calculated from option price vs. IBKR model Greeks
  • assignment_prob_pct — N(d2): risk-neutral probability the short expires ITM
  • net_credit — credit received when rolling (negative = debit); rolls with debit > $0.10/share excluded
  • pnl_if_assigned — P&L if underlying finishes above short_strike at expiry: (short_strike - long_strike - long_cost + total_premium) × 100
  • daily_pnl[].optimal_spot — spot price that maximises exit P&L on that day (found via numerical optimisation); increases as theta decays the short leg
  • daily_pnl[].pnl — total dollars (qty × 100 contracts) at the optimal spot on that day

Roll Selection Criteria

Candidates must satisfy both:

  1. Delta ≤ 0.40 (absolute cap — allows same-strike forward rolls when current short is near expiry)
  2. Net credit ≥ -$0.10/share (not a large debit)

Scans the next 5 available chain expirations after the current short expiry, bounded by the LEAPS expiry.

Ranked by: delta improvement (highest weight) → net credit → DTE extension.

Example Usage

# All accounts (paper, default)
uv run python .claude/skills/ib-pmcc-advisor/scripts/pmcc_advisor.py

# Live account, 14-day minimum roll DTE, last-price mode
uv run python .claude/skills/ib-pmcc-advisor/scripts/pmcc_advisor.py --port 7496 --account Uxxxxxxxx --min-roll-dte 14 --price-mode last

# Analyze only specific symbols
uv run python .claude/skills/ib-pmcc-advisor/scripts/pmcc_advisor.py --symbols NVDA WMT

Architecture

All logic lives in src/trading_skills/broker/pmcc_advisor.py:

  • Analytics functions (top half, no IBKR imports): get_option_price, calc_iv, calc_delta, calc_assignment_prob, calc_bs_price, calc_daily_pnl_table, check_earnings_warning, find_best_rolls, build_comparison_table, score_roll_candidate
  • Data layer (bottom half, uses IBKR + Yahoo Finance): get_pmcc_data, _identify_pmcc_spreads, _fetch_single_option_quote, _fetch_option_quotes_batch, _get_chain_params, _fetch_earnings_dates

Reuses from src/trading_skills/broker/:

  • connection.py — ib_connection, CLIENT_IDS, fetch_positions, fetch_spot_prices, normalize_positions, best_option_chain
  • black_scholes.py — implied_volatility, black_scholes_price, black_scholes_delta, estimate_iv

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.