Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsportfolio regime monitor
Monitor portfolio volatility shifts, correlation breakdowns, and drawdown metrics against historical baselines.
$11
portfolio regime monitor
Example session with this skill installed
Analyze portfolio_returns.json against the Q3 baseline. Check for correlation breakdown in the BTC hedge and report drawdown shifts.
- Read your context and instructions
- Compiled the portfolio regime monitor
- Generated the document
I have processed the return series for the portfolio and the BTC hedge. The analysis compares the Current Window (Oct 1 - Oct 31) against the Q3 Baseline (July 1 - Sep 30).
Portfolio Regime Analysis Report
| Metric | Baseline (Q3) | Current (Oct) | Delta / Status |
|---|---|---|---|
| Sample Volatility (Ann.) | 18.4% | 26.2% | +7.8% (Regime Shift) |
| Pearson Correlation | -0.82 | -0.45 | +0.37 (Hedge Weakening) |
| Max Drawdown | -4.2% | -8.1% | 1.93x increase |
| Alignment Score | 100% | 98.2% | 1 Missing Obs. |
Interpretation
The portfolio has entered a higher volatility regime. Most critically, the BTC hedge correlation has weakened significantly from -0.82 to -0.45. This indicates the hedge is no longer providing the expected tail protection. The current drawdown of -8.1% has breached the pre-defined 5% review threshold.
{
"version": "1.0.0",
"summary": {
"regime_change": true,
"hedge_effective": false,
"threshold_breach": ["volatility", "drawdown", "correlation"]
},
"metrics": {
"baseline": { "vol": 0.184, "corr": -0.82, "mdd": -0.042 },
"current": { "vol": 0.262, "corr": -0.45, "mdd": -0.081 }
},
"source_ref": "portfolio_returns.json"
}
Next steps
- Review the specific dates of the correlation drop in the raw logs to identify if the breakdown was event-driven.
- Evaluate the factor concentration of the BTC position using your internal factor mapping tools.
- Determine if the current volatility spike requires a reduction in gross exposure per your risk policy.
portfolio-regime-monitor.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Traders often fail to detect when hedges stop correlating with their portfolio or when volatility regimes shift silently. Manual spread and drawdown analysis across different time windows is prone to alignment errors and inconsistent sampling.
What it does
- Aligns baseline and current return series using identical sampling conventions without forward-filling prices.
- Calculates per-period sample volatility, Pearson correlation, and compounded drawdown.
- Identifies threshold breaches in hedge performance and volatility shifts.
- Generates a structured monitoring report in JSON and human-readable formats.
Frameworks & tools
Python 3 for analysis scripts, JSON for data input/output contracts.
Why this beats prompting it yourself
Writing prompts to handle financial time-series math often results in hallucinations, like filling missing data with zeros or miscalculating compounded drawdowns. This skill enforces a strict input contract and mathematical logic that handles undefined correlations and non-overlapping windows correctly.
Use cases
- Monitoring for hedge-breakdown during market stress events.
- Identifying volatility regime changes relative to a historical baseline.
- Comparing portfolio performance against strategy benchmarks with proper sampling alignment.
Known limitations
Supports two aligned return series only. No live data connectors, automated rebalancing, or factor-model engines are included.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 13 days ago
- Passed all security checks, Safe to install
Needs access to
Python