ib-collar
Skill411 starsChanged 9 days agoMITView on GitHub
Generate tactical collar strategy reports for protecting PMCC positions through earnings or high-risk events. Requires TWS or IB Gateway running locally.
- Reads credentials
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- calendarSkill
- chart-ema-rsiSkill
- earnings-calendarSkill
- fundamentalsSkill
- greeksSkill
- ib-accountSkill
- ib-create-consolidated-reportSkill
- ib-find-short-rollSkill
- ib-option-chainSkill
- ib-pmcc-advisorSkill
- ib-portfolio-action-reportSkill
- ib-portfolioSkill
- ib-report-delta-adjusted-notional-exposureSkill
- ib-stop-lossSkill
- ib-trades-historySkill
- ib-trailing-stopSkill
- insider-tradingSkill
- markdown-to-pdfSkill
- news-sentimentSkill
- option-chainSkill
- price-historySkill
- report-stockSkill
- risk-assessmentSkill
- scanner-bullishSkill
- scanner-pmccSkill
- spread-analysisSkill
- stock-quoteSkill
- technical-analysisSkill
- whale-huntingSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 18
Port fallback: If the configured port fails, automatically retry on the other port.
- Distinctive: line 19
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 …
- Distinctive: line 20
If both ports fail, ask the user to verify that TWS or IB Gateway is running with API access enabled.
- Very specific: line 34
Read templates/markdown-template.md for formatting instructions.
- Distinctive: line 74
No additional margin required for collar
- Very specific: line 107
All timestamps and time-based calculations must use the America/New_York timezone.
≈ “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.
Files
IB Tactical Collar
Generate a tactical collar strategy report for protecting PMCC positions through earnings or high-risk events.
IB Connection
TWS or IB Gateway must be running locally with API enabled:
- Paper trading — port 7497
- Live trading — port 7496
IB_PORTenv var — default port when--portis omitted (e.g.IB_PORT=4001for a Gateway container). Precedence:--portflag >IB_PORT> built-in default. Set it in the shell or a.envfile.
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
uv run python scripts/collar.py SYMBOL [--port PORT] [--account ACCOUNT]The script returns JSON to stdout with all position and scenario 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 put protection, cost/benefit, and the saved report path.
Arguments
SYMBOL- Stock symbol to analyze (must be in portfolio)--port- IB port (default: 7497 for paper trading)--account- Specific account ID (optional, searches all accounts)
JSON Output
The script returns JSON with these key fields:
symbol,current_price- Basic infolong_strike,long_expiry,long_qty,long_cost- LEAPS positionshort_positions- List of short callsis_proper_pmcc,short_above_long- PMCC health flagsearnings_date,days_to_earnings- Earnings timingput_analysis- List of put scenarios with costs and P&L under gap up/flat/downunprotected_loss_10,unprotected_loss_15,unprotected_gain_10- LEAPS risk without collarvolatility- Historical volatility data
Report Sections
- Position Summary: Current PMCC structure (long calls, short calls)
- PMCC Health Check: Is structure proper (short > long strike) or broken?
- Earnings Risk: Next earnings date and days until event
- Put Duration Analysis: Comparison of short vs medium vs long-dated puts
- Collar Scenarios: Gap up, flat, gap down outcomes with each put duration
- Cost/Benefit Analysis: Insurance cost vs protection value
- Implementation Timeline: Step-by-step checklist with dates
- Recommendation: Optimal put strike and expiration
Key Concepts
Proper PMCC Structure:
- Long deep ITM LEAPS call
- Short OTM calls ABOVE long strike
- No additional margin required for collar
Broken PMCC Structure:
- Long call is now OTM (after crash)
- Short calls BELOW long strike require margin
- Collar still works but margin implications exist
Tactical Collar:
- Buy protective puts ONLY before high-risk events (earnings)
- Sell puts after event passes
- Balances income generation with crash protection
Put Duration Trade-offs:
- Short-dated: Cheaper, more gamma, but zero salvage on gap up
- Medium-dated (2-4 weeks): Best balance of cost, gamma, and salvage
- Long-dated: Preserves value on gap up, but expensive and less gamma
Example Usage
# Analyze NVDA position (defaults to paper port 7497)
uv run python scripts/collar.py NVDA
# Analyze specific account
uv run python scripts/collar.py AMZN --account U790497
# Use paper trading port instead
uv run python scripts/collar.py NVDA --port 7497Timezone
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.
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
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.

