portfolio-risk skillB
portfolio-risk is agent-read markdown (skill) from orkas-ai/orkas.
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
# Portfolio Risk
Read with `market-data` for a portfolio review, stress test, or rebalance
question. Keep account values and holdings private and use only what is needed.
Choose the calculation from the supplied data: `--mode historical` (default)
requires aligned daily decimal returns; `--mode scenario` uses weights and
declared shocks, returns no historical statistics, and needs no return series.
Do not manufacture a series to make a scenario request fit historical mode.
Historical input uses weights that sum to one and aligned daily decimal returns:
```json
{"positions":[{"symbol":"700.HK","weight":0.4,"currency":"HKD","sector":"Technology","returns":[0.01,-0.02]}],"scenarios":{"tech_down":{"Technology":-0.15}}}
```
Run:
```bash
"$ORKAS_NODE" "$ORKAS_PC_DIR/bin/run-skill.cjs" market-data stock -- portfolio-risk --input portfolio.json --confidence 0.95
```
The core calculates portfolio return series from aligned observations, annual
volatility, max drawdown, historical VaR/CVaR, HHI and top-name concentration,
sector/currency exposure, and declared linear scenario losses. VaR is a sample
statistic, not a loss ceiling.
…Read the whole file at its exact version.
How to install
mdr add orkas-ai/orkas/portfolio-risk@git:20260921.838ca9amdr add orkas-ai/orkas/portfolio-risk@sha256:d878a3d82373ba5fPin 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_exa7a25wnmi33k27)
1 badge views in 30 days
Versions
Audit of the latest version
- fail: Frontmatter declares a description
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Size between 200 bytes and 200 KB (2722 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
orkas-ai/orkas · 2,113 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_exa7a25wnmi33k27 GET https://markdownregistry.com/api/v1/resolve?ref=orkas-ai/orkas/portfolio-risk GET https://markdownregistry.com/api/v1/blob/d878a3d82373ba5f0af9f3a0b7cde88922b56974e8c84da88e2f70ac6e7737c8
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.