Full Empirical Analysis

Full Empirical Analysis is a Data skill for Claude Code, published by brycewang-stanford in Auto-Empirical-Research-Skills.

3.4K stars445 forkson brycewang-stanford/Auto-Empirical-Research-SkillsAdded 2026/08/16+1% in starsRepository updated 2026/08/10

View source on GitHub Download repo ZIP

academic-researchagent-skillsai-agentawesome-listcommunicationcopapereconomicseducationempirical-researchinternational-relationspolitical-sciencepsychologypublic-administrationreproducible-researchskills-librarysocial-sciencesociology

Install in seconds

Install Full Empirical Analysis

Copy Full Empirical Analysis into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/00.1-Full-empirical-analysis-skill_Python ~/.claude/skills/00.1-Full-empirical-analysis-skill_Python

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/00.1-Full-empirical-analysis-skill_Python/SKILL.md in brycewang-stanford/Auto-Empirical-Research-Skills
Installs to: ~/.claude/skills/00.1-Full-empirical-analysis-skill_Python
Collection: One of 25 skills cataloged from this repository
Category: Data — 668 skills

What Full Empirical Analysis does

Full Empirical Analysis provides a complete end-to-end workflow for applied empirical research in Python, covering data cleaning, variable construction, descriptive statistics, econometric modeling, robustness checks, and publication-ready tables and figures. It also includes specialized modes for target-trial emulation and ML causal inference, with explicit library choices and diagnostic steps.

Full Empirical Analysis is cataloged under Data on DirSkills. Full Empirical Analysis comes from a repository tagged academic-research, agent-skills, ai-agent, awesome-list and communication.

Documentation

README

Excerpt

Full Empirical Analysis — Classical Python Workflow

This skill is the canonical 8-step pipeline an applied economist runs on every empirical paper, written in the traditional Python ecosystem — no opinionated one-stop wrapper. Every step calls libraries directly (pandas, numpy, scipy, statsmodels, linearmodels, pyfixest, rdrobust, econml, causalml, matplotlib, seaborn), so the agent — or the user reading the agent's code — has full visibility and can swap any component.

Companion skill: if the user prefers a single-import agent-native DSL (import statspai as sp), route to 00-StatsPAI_skill instead. This skill is the opposite philosophy: everything explicit, everything inspectable, every diagnostic run by hand, every plot shaped by the user.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Full Empirical Analysis

What else does brycewang-stanford publish alongside Full Empirical Analysis?
Full Empirical Analysis is one of 25 skills that DirSkills catalogs from brycewang-stanford/Auto-Empirical-Research-Skills, the repository it ships in. Its siblings there include Academic Paper Composer, Academic Proofreader and Auto-Empirical Research. Each one is a separate skill with its own page in this directory, installs the same way Full Empirical Analysis does, and is maintained by brycewang-stanford in that same repository. The rest of the collection is listed on the brycewang-stanford/Auto-Empirical-Research-Skills page.
How does Full Empirical Analysis compare to other Data skills?
Full Empirical Analysis ranks #201 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Full Empirical Analysis against them. Open each page to compare what they document and how they install.