Macro Regime

This skill should be used when the user asks to "classify the macro regime", "score expansion versus recession", or create a dated regime signal for capital market assumptions and SAA research.

5 starsResearch & Science Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add nutdnuy/self-driving-portfolio-skill

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add nutdnuy/self-driving-portfolio-skill --skill macro-regime
Manual install
git clone --depth 1 https://github.com/nutdnuy/self-driving-portfolio-skill.git /tmp/self-driving-portfolio-skill
mkdir -p ~/.claude/skills
cp -r /tmp/self-driving-portfolio-skill/skills/macro-regime ~/.claude/skills/macro-regime

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# macro-regime

The 4-regime classifier from Ang/Azimbayev/Kim (2026) §3.2.

## Methodology

Four indicator families are scored on a [-1, +1] scale (positive = "hot",
negative = "cold"). Each family is a z-score of recent readings vs a
rolling 5-year baseline.

| Family                | FRED series                          |
| --------------------- | ------------------------------------ |
| Growth                | INDPRO (industrial production, YoY)  |
| Inflation             | CPIAUCSL (headline CPI YoY)          |
| Monetary policy       | DFF − T10Y3M (real-curve proxy: fed funds minus 10y-3m spread) |
| Financial conditions  | NFCI (Chicago Fed; positive = tight) |

The regime score is a fixed-weight projection (paper §3.2):

```
expansion  =  +growth  −0.5·inflation  −0.5·monetary  −1.0·fci
late_cycle =  +growth  +1.0·inflation  +1.0·monetary  +0.5·fci
recession  =  −growth  −0.5·inflation  +0.0·monetary  +1.0·fci
recovery   =  +growth  −1.0·inflation  −1.0·monetary  −0.5·fci
```

Scores are softmax-normalised across the four labels. The argmax is the
regime label; the full vector is exposed downstream.

## Scripts

- `scripts/fetch_macro.py` — pull an authenticated FRED vintage when
  `FRED_API_KEY` is set; otherwise apply the observation-date cutoff to
  latest-revised public CSV history and disclose that policy in the artifact.
- `scripts/classify_regime.py` — runs the scoring, writes `regime.json`.

## Output contract
Read the full skill on GitHub

Details

Skill name
macro-regime
Path
skills/macro-regime/SKILL.md
License
MIT
Repo updated
29 August 2026

FAQ

What does the Macro Regime skill do?

This skill should be used when the user asks to "classify the macro regime", "score expansion versus recession", or create a dated regime signal for capital market assumptions and SAA research.

How do I install the Macro Regime skill?

Claude Code plugin: /plugin marketplace add nutdnuy/self-driving-portfolio-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Macro Regime popular?

It lives in nutdnuy/self-driving-portfolio-skill, which has 5 GitHub stars and 0 forks.

Related skills

Asset Class Cma

5

nutdnuy/self-driving-portfolio-skill

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.

Finance & Crypto

Cio Ensemble

5

nutdnuy/self-driving-portfolio-skill

This skill should be used when the user asks to "combine portfolio proposals", "build a CIO ensemble", "select an SAA recommendation", or "write a portfolio board memo" from reviewed candidates.

Finance & Crypto

Covariance

5

nutdnuy/self-driving-portfolio-skill

This skill should be used when the user asks to "estimate a covariance matrix", "run Ledoit-Wolf shrinkage", "build an EWMA covariance", or validate PSD risk inputs for portfolio construction.

Finance & Crypto

Pilot Scientific Research Team Setup

9

TeoSlayer/pilot-skills

Deploy a scientific research team with 4 agents. Use this skill when: 1. User wants to set up a collaborative research pipeline with literature review, hypothesis generation, experimentation, and reporting 2. User is configuring agents for automated scientific discovery workflows 3. User asks about research automation, hypothesis testing pipelines, or experiment management Do NOT use this skill when: - User wants a single literature search (use pilot-discover instead) - User wants to share a file between two agents (use pilot-share instead) - User only needs data archival (use pilot-archive in

Research & Science

Auto Research

9

huytran1120/vietnam-agentic-skills

Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.

Research & Science

Pilot Service Agents Academic

9

TeoSlayer/pilot-skills

Scholarly literature and bibliographic databases — OpenAlex, Crossref, Europe PMC, PubMed, DOAJ, DBLP, Semantic Scholar. Use this skill when: 1. Searching peer-reviewed works by author, title, keyword, or DOI 2. Walking the citation / funder / institution graph (OpenAlex) 3. Looking up a DBLP author page or a ROR organisation record Do NOT use this skill when: - Full-text article download — agents return metadata only - Clinical guideline search (use pilot-service-agents-health — clinicaltrials, PubMed eSearch is in `academic`) - Book catalog search (use pilot-service-agents-books)

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.