ml4t-risk-metrics skillA
ml4t-risk-metrics is agent-read markdown (skill) from ml4t/skills: Compute portfolio risk measures including drawdown, VaR, CVaR, and tail metrics. Use when assessing portfolio risk beyond simple return statistics..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Risk Metrics
A strategy with Sharpe 1.5 and max drawdown -55% will get shut down before it recovers. Reporting returns without drawdowns, tail risk, and duration metrics hides the path dependency that determines whether a strategy survives.
## The Problem
Sharpe ratio is the default performance metric, but it treats upside and downside volatility equally and says nothing about tail losses. A strategy can have a high Sharpe while hiding a -40% drawdown that takes 18 months to recover. Fund managers and allocators care about max drawdown, time underwater, and worst-case losses - because those determine whether the strategy (and the fund) survives. Always report drawdown alongside return metrics.
## The Pattern
### WRONG
```python
import numpy as np
returns = strategy_returns # daily
sharpe = returns.mean() / returns.std() * np.sqrt(252)
print(f"Sharpe: {sharpe:.2f}") # Looks great - ships it
```
### CORRECT
```python
import numpy as np
from scipy.stats import norm
returns = strategy_returns # daily, numpy array
# Return metrics
sharpe = returns.mean() / returns.std() * np.sqrt(252)
downside = np.minimum(returns, 0) # All returns: negative kept, positive → 0
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-risk-metrics@git:20260901.c415df0mdr add ml4t/skills/ml4t-risk-metrics@sha256:6b1840c03b129627Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_lc3veuziw5sqyfah)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.c415df0 latest | 2026-09-01 | c415df0 | 4,121 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,131 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4121 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ml4t/skills · 19 stars · license Apache-2.0 · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lc3veuziw5sqyfah GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-risk-metrics GET https://markdownregistry.com/api/v1/blob/6b1840c03b12962790f162434af701ea0178e6d093da9575c2d7d3e46aac2ca1
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.