# Asset Class Cma

> This skill should be used when the user asks to "build capital market assumptions", "estimate asset-class returns", or create regime-conditioned return, volatility, and confidence inputs for portfolio construction.

- **Type:** Skill
- **Install:** `agentstack add skill-nutdnuy-self-driving-portfolio-skill-asset-class-cma`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [nutdnuy](https://agentstack.voostack.com/s/nutdnuy)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [nutdnuy](https://github.com/nutdnuy)
- **Source:** https://github.com/nutdnuy/self-driving-portfolio-skill/tree/main/skills/asset-class-cma

## Install

```sh
agentstack add skill-nutdnuy-self-driving-portfolio-skill-asset-class-cma
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# asset-class-cma

Given a list of tickers and the regime classification, produce a CMA per
ticker.

## Methodology

1. Pull adjusted close prices via yfinance (default 10y daily lookback) and
   reject every row after the shared as-of date.
2. Compute geometric mean return and annualised volatility from log-returns.
3. Apply a regime-conditional tilt to expected return:

   | Asset class proxy | expansion | late_cycle | recession | recovery |
   | --- | --- | --- | --- | --- |
   | Equities (SPY, EFA, EEM, VNQ) | +1.5% | −0.5% | −3.0% | +2.0% |
   | Treasuries (IEF, BIL)         | −0.5% | −0.5% | +1.5% | +0.5% |
   | Credit (LQD)                  |  0.0% | −1.0% | −1.5% | +1.0% |
   | Inflation-linked (TIP, GLD)   | +0.5% | +1.5% | +0.0% | −0.5% |

   Tilts are scaled by the regime's softmax probability so that a
   low-confidence call applies a smaller tilt.

4. Confidence (0–1) = sample-size factor × vol-stability factor
   × regime-confidence factor.

Stop when any IPS ticker is unavailable or has fewer than 60 usable returns.
Never shrink the mandate universe silently.

## CLI

```bash
python skills/asset-class-cma/scripts/build_cma.py \
       --regime outputs/demo01/regime.json \
       --tickers SPY,EFA,EEM,IEF,LQD,TIP,GLD,VNQ,BIL \
       --as-of 2026-05-08 \
       --out outputs/demo01/cmas.json
```

Run through `pipeline/orchestrator.py` for schema gating and governed output.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [nutdnuy](https://github.com/nutdnuy)
- **Source:** [nutdnuy/self-driving-portfolio-skill](https://github.com/nutdnuy/self-driving-portfolio-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-nutdnuy-self-driving-portfolio-skill-asset-class-cma
- Seller: https://agentstack.voostack.com/s/nutdnuy
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.