How do I install the Factor Model Project skill?

Run npx skillmds@latest add knuckles-team/factor-model-project in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Factor Model Project safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Factor Model Project?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Factor Model Project free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Factor Model Project?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Factor Model Project by knuckles-team

Name: Factor Model Project
Author: Knuckles-Team

Factor Model Project

Build the Fama-French 3-factor portfolio project: download the free factor data from Kenneth French's website, regress a portfolio's returns against market, size, and value factors, interpret the loadings, and publish a GitHub repo.

Knuckles-Team cb06f67 2 files · 2.9 KB Updated Sep 17, 2026

File contents

Factor Model Project Workflow

Project 2 of the quant portfolio. Replicate the Fama-French 3-factor model (market beta, size, value). See quant-career-docs/reference/strategies.md.

Steps

Step 1: fetch-french-factors

Agent: quant_researcher Tools: data-science-mcp

Download the Fama-French 3-factor data (Mkt-RF, SMB, HML, RF) from Kenneth French's website. Align the date index. Expected: factor-returns

Step 2: fetch-returns

Agent: quant_developer Tools: data-science-mcp

Pull returns for a portfolio or asset under study via yfinance; compute excess returns over the risk-free rate. Expected: excess-returns

Step 3: regress-factors [depends_on: Step 1, Step 2]

Agent: quant_researcher

Regress excess returns on the three factors (OLS via statsmodels). Capture coefficients, t-stats, and R-squared. Expected: factor-loadings

Step 4: interpret-loadings [depends_on: Step 3]

Agent: quant_researcher

Interpret the loadings (market/size/value tilt) and alpha. State what the model does and does not explain — honest analysis. Expected: factor-interpretation

Step 5: github-publish [depends_on: Step 4]

Agent: quant_developer

Publish a GitHub repo with README, regression results, clean code, and an honest "what didn't work" section. Expected: github-repo-url

Step 6: kg-persist [depends_on: Step 5]

Agent: quant_researcher Tools: graph_write

Persist the project and factor loadings as typed nodes linked to the portfolio.

Output

A reproduced Fama-French 3-factor regression with interpreted loadings
A published GitHub portfolio repo

Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet depends_on run in parallel; dependents run after their prerequisites complete.

Run first (in parallel): Step 1 — fetch-french-factors; Step 2 — fetch-returns
After level 0: Step 3 — regress-factors
After level 1: Step 4 — interpret-loadings
After level 2: Step 5 — github-publish
After level 3: Step 6 — kg-persist

Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

---name: factor-model-projectdescription: Build the Fama-French 3-factor portfolio project: download the free factor data from Kenneth French's website, regress a portfolio's returns against market, size, and value factors, interpret the loadings, and publish a GitHub repo.---# Factor Model Project WorkflowProject 2 of the quant portfolio. Replicate the Fama-French 3-factor model (marketbeta, size, value). See `quant-career-docs/reference/strategies.md`.## Steps### Step 1: fetch-french-factors**Agent**: `quant_researcher`**Tools**: `data-science-mcp`Download the Fama-French 3-factor data (Mkt-RF, SMB, HML, RF) from KennethFrench's website. Align the date index.Expected: `factor-returns`### Step 2: fetch-returns**Agent**: `quant_developer`**Tools**: `data-science-mcp`Pull returns for a portfolio or asset under study via yfinance; compute excessreturns over the risk-free rate.Expected: `excess-returns`### Step 3: regress-factors [depends_on: Step 1, Step 2]**Agent**: `quant_researcher`Regress excess returns on the three factors (OLS via statsmodels). Capturecoefficients, t-stats, and R-squared.Expected: `factor-loadings`### Step 4: interpret-loadings [depends_on: Step 3]**Agent**: `quant_researcher`Interpret the loadings (market/size/value tilt) and alpha. State what the modeldoes and does not explain — honest analysis.Expected: `factor-interpretation`### Step 5: github-publish [depends_on: Step 4]**Agent**: `quant_developer`Publish a GitHub repo with README, regression results, clean code, and an honest"what didn't work" section.Expected: `github-repo-url`### Step 6: kg-persist [depends_on: Step 5]**Agent**: `quant_researcher`**Tools**: `graph_write`Persist the project and factor loadings as typed nodes linked to the portfolio.## Output- A reproduced Fama-French 3-factor regression with interpreted loadings- A published GitHub portfolio repo## ExecutionRun this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.- **Run first (in parallel):** Step 1 — fetch-french-factors; Step 2 — fetch-returns- **After level 0:** Step 3 — regress-factors- **After level 1:** Step 4 — interpret-loadings- **After level 2:** Step 5 — github-publish- **After level 3:** Step 6 — kg-persist**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.

Frequently asked questions