ml4t-exposure-analysis skillA
ml4t-exposure-analysis is agent-read markdown (skill) from ml4t/skills: Decompose portfolio into factor, sector, and concentration exposures. Use when checking for unintended bets or risk concentrations..
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
# Exposure Analysis
A portfolio of 50 stocks can look diversified by count while having 80% of its risk in a single factor. Without exposure decomposition, you cannot distinguish between intended alpha bets and unintended factor tilts.
## The Problem
Position weights tell you what you own, not what risks you are taking. A "diversified" tech-heavy portfolio may have a market beta of 1.4, a momentum loading of +0.6, and 60% sector concentration in technology - meaning most of its variance comes from three correlated bets, not 50 independent ones. Exposure analysis decomposes portfolio risk into factor loadings, sector weights, and concentration measures so you can verify that the portfolio matches your thesis.
## The Pattern
### WRONG
```python
import numpy as np
# Only look at position weights
weights = np.array([0.05, 0.04, 0.03, ...]) # 50 stocks
print(f"Number of positions: {len(weights)}")
print(f"Max position: {weights.max():.1%}")
# "50 positions, max 5% - looks diversified!"
# But 35 of them are correlated growth stocks with beta > 1.3
```
### CORRECT
```python
import numpy as np
from sklearn.linear_model import LinearRegression
# Factor exposure via regression
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-exposure-analysis@git:20260901.c415df0mdr add ml4t/skills/ml4t-exposure-analysis@sha256:1da5e316eb9f4b61Pin 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_okkizzu2qrjan7ac)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.c415df0 latest | 2026-09-01 | c415df0 | 4,448 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 4,460 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 (4448 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_okkizzu2qrjan7ac GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-exposure-analysis GET https://markdownregistry.com/api/v1/blob/1da5e316eb9f4b61a506be651603a7b1d2dac508ece1112483b72baf381f22d5
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.