pipeline
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy +…
College Scorecard — post-enrollment outcomes linking aid records to IRS/Treasury earnings. Earnings, loan repayment, debt via six Portal sub-datasets. Use when tax-record-based earnings needed. Tracks only Title IV aid recipients, not all students.
Claude Code
$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-source-scorecard --agent claude-code
Codex
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-source-scorecard -a codex -y
Cursor
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-source-scorecard -a cursor -y
Gemini CLI
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-source-scorecard -a gemini-cli -y
GitHub Copilot
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-source-scorecard -a github-copilot -y
OpenCode
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-source-scorecard -a opencode -y
Windsurf
$ npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-source-scorecard -a windsurf -y
name: education-data-source-scorecard description: >- College Scorecard — post-enrollment outcomes linking aid records to IRS/Treasury earnings. Earnings, loan repayment, debt via six Portal sub-datasets. Use when tax-record-based earnings needed. Tracks only Title IV aid recipients, not all students. metadata: audience: any-agent domain: data-source skill-authored: "2026-02-09" skill-last-updated: "2026-02-09"
College Scorecard — the primary institutional-level source for post-enrollment labor market outcomes, linking NSLDS financial aid records to IRS/Treasury earnings data. Use when comparing institutions on post-graduation earnings, loan repayment, or student debt, or when actual tax-record-based earnings are required rather than survey estimates. Covers six sub-datasets accessed via Portal mirrors. Critical limitation: tracks only Title IV federal aid recipients, not all students.
Federal data on post-college outcomes including earnings, debt, and repayment for students who received Title IV financial aid. Links education records to IRS tax data for actual earnings, making it the primary source for post-college labor market outcomes.
> **CRITICAL: Value Encoding and Missing Data** > > The Education Data Portal uses **integer encodings** for all categorical variables > and **lowercase, restructured variable names** that differ from the original > Scorecard column names. Suppression encoding differs by dataset: > > - **Earnings/counts**: `-3` integer code is the primary suppression indicator > - **Yes/No flags** (institutional characteristics): `null` for missing, `0`/`1` for valid > - **Rates** (repayment, default): `null` for missing > - The original Scorecard string `"PrivacySuppressed"` does NOT appear in Portal data > > | Context | `pred_degree_awarded_ipeds` | HBCU / tribal flags | `religious_affiliation` | > |---------|----------------------------|---------------------|-------------------------| > | **Portal (integer)** | `0`-`4` | `0` / `1` | Integer codes 22-200 | > | Original Scorecard | String labels | String labels | String labels | > > See `./references/variable-definitions.md` for complete encoding tables.
| File | Purpose | When to Read | |------|---------|--------------| | `earnings-data.md` | Post-college earnings methodology, cohorts, time horizons | Analyzing earnings outcomes | | `debt-repayment.md` | Student debt, repayment rates, default rates | Analyzing debt or loan outcomes | | `completion-rates.md` | Completion metrics vs IPEDS | Comparing graduation rates | | `population-coverage.md` | Title IV limitation details, who is included/excluded | Understanding data representativeness | | `variable-definitions.md` | Key variables, naming conventions, special values | Building queries or interpreting results | | `data-quality.md` | Suppression rules, selection bias, known limitations | Assessing data reliability | | `field-of-study.md` | Program-level earnings and debt data | Analyzing outcomes by major/CIP code |
Outcome type?
├─ Post-college earnings
│ ├─ Institution-level → ./references/earnings-data.md
│ └─ By field of study → ./references/field-of-study.md
├─ Student debt levels
│ ├─ Cumulative borrowing → ./references/debt-repayment.md
│ └─ Debt by field → ./references/field-of-study.md
├─ Loan repayment/default
│ └─ Repayment rates → ./references/debt-repayment.md
├─ Completion rates
│ └─ Scorecard completion → ./references/completion-rates.md
└─ Understanding limitations
├─ Who is included → ./references/population-coverage.md
└─ Data quality issues → ./references/data-quality.mdInterpretation question?
├─ Why are earnings suppressed?
│ └─ Privacy thresholds → ./references/data-quality.md
├─ What does "6-year earnings" mean?
│ └─ Cohort timing → ./references/earnings-data.md
├─ Why don't Scorecard rates match IPEDS?
│ └─ Different cohorts → ./references/completion-rates.md
├─ What loans are included in debt?
│ └─ Federal only → ./references/debt-repayment.md
└─ How representative is this data?
└─ Title IV coverage → ./references/population-coverage.mdQuery construction? ├─ Variable names and codes → ./references/variable-definitions.md ├─ Suppression flags to handle → ./references/data-quality.md ├─ Understanding cohort years → ./references/earnings-data.md └─ Field-level queries → ./references/field-of-study.md
The Portal uses **LONG format** with time horizon as a column, NOT the WIDE format from original Scorecard bulk download files. **Portal column names are all lowercase** and differ significantly from original Scorecard names.
| Original Scorecard (WIDE) | Portal Column (LONG) | How to Get | |---------------------------|----------------------|------------| | `MD_EARN_WNE_P6` | `earnings_med` | Filter: `years_after_entry == 6` | | `MD_EARN_WNE_P10` | `earnings_med` | Filter: `years_after_entry == 10` | | `COUNT_WNE_P6` | `count_working` | Filter: `years_after_entry == 6` | | `MN_EARN_WNE_P6` | `earnings_mean` | Filter: `years_after_entry == 6` | | `CONTROL`, `INSTNM` | NOT
## 🔥 力荐 · StatsPAI — Stata 与 R 的 Python 平替,为 AI Agent 而生 🔁 Stata / R 平替:reghdfe、csdid、rdrobust、synth、fixest、did 等常用命令在 Python 中一站式替代,一个 import statspai as sp 搞定 DID / RD / IV / SCM / DML / matching 🤖 面向 Agent 设计:结构化结果对象 + 内置 MCP Server,Claude / Codex
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy +…
Use when the user asks to run a full empirical / causal analysis in Python — by default in the style of an applied economics…
Classical end-to-end empirical analysis workflow in the traditional Python econometric stack — pandas + numpy + scipy +…
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid +…
Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven +…
Systematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…