๐ฌ A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | A curated collection of 23,000+ AI Agent skills covering empirical research in 8 social science disciplines. CoPaper.AI completes a reproducible, rigorous empirical paper in 20 minutes and supports user-uploaded Skills. -- Maintained by CoPaper.AI from Stanford REAP.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Discovers education data from Urban Institute Portal: endpoints, variables, year coverage, join keys (CCD, IPEDS, CRDC, Scorecard, SAIPE). Use to map questions to data. Load before education-data-query โ discovery here, download there.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Downloads education datasets from configured mirror sources (parquet/CSV) with local Polars filtering. Use when writing fetch scripts or retrieving CCD, IPEDS, CRDC, SAIPE data. Load after education-data-explorer โ retrieval here, not discovery.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
CSS โ annual Clery Act crime/fire safety for Title IV institutions. Portal: hate crimes only (2005-2021); primary offenses, VAWA, arrests, fire safety need ope.ed.gov directly. Use for campus crime analysis. Identified by IPEDS unitid.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
CCD โ federal universe of all U.S. public K-12 schools (100K) and districts (18K). Enrollment, staffing, finance, directory data (1986-present). Use for public school analysis by grade/race/sex. Public only; excludes private and postsecondary.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
CRDC โ biennial OCR survey of all U.S. public schools (2011-2021). Discipline, course access, harassment, restraint/seclusion by race/sex/disability/EL. Use for civil rights and equity analysis. 2020-21 COVID-impacted; 2011-14 sampled, not universe.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
EADA โ college athletics gender equity (2,000+ institutions, 2002-2021). Participation, coaching, salaries, expenses, revenues, athletic aid by gender. Not Title IX compliance data. No sector column; join IPEDS on unitid for institution type.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
EDFacts โ K-12 outcomes: assessment proficiency, ACGR graduation rates, ESSA accountability at school/district level (2009-2020). Within-state trends and subgroup gaps. Complements CCD with outcome data. Cannot compare across states โ use NAEP.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
FSA โ Title IV aid at institution level (5,500 institutions, 1999-2021). Pell Grants, Direct/PLUS loans, campus-based aid, financial responsibility scores, 90/10 metrics. Use for aid distribution, loan volume, or for-profit analysis. By unitid.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
IPEDS โ primary federal postsecondary data (6,500 institutions, 1980-present): enrollment, completions, graduation rates, finance, aid, admissions, HR. For college/university analysis. Grad rates = first-time full-time; finance needs GASB/FASB care.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
MEPS โ Urban Institute modeled school-level poverty (% at 100% FPL), from CCD + SAIPE (public schools, 2009-2022, 2-3yr lag). Use when FRPL is unreliable due to CEP. Consistent cross-state measurement. Public schools only.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
NACUBO endowment data (650 institutions, 2012-2022). Portal: 7 columns only (total endowment, per-FTE, YoY change). Use for endowment size/trends. Full investment/spending needs direct NACUBO access. For all-institution coverage use IPEDS finance.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
NCCS โ Form 990 data for private nonprofit colleges (Portal: IPEDS-matched, 1993-2016). Revenue, expenses, assets, endowment, governance beyond IPEDS. Use when IRS financial depth needed. Portal ends 2016; public institutions excluded (no Form 990).
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
NHGIS โ census geography crosswalks via Portal: links schools (ncessch) and colleges (unitid) to tracts, block groups, CBSAs (1990-2020). Census demographics NOT in Portal โ access NHGIS directly. Use for linking education data to census geography.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
PSEO โ Census data linking graduates to employment via LEHD wage records. Earnings percentiles at 1/5/10 years post-graduation by institution, degree, CIP. Use for graduate earnings analysis. Coverage: 29% of graduates from 31 states.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
SAIPE โ annual Census poverty estimates for school districts (Portal; county/state not in Portal). Use for district poverty, Title I context, or trends. 18-month lag. No race/ethnicity disaggregation at district level โ use ACS 5-year for that.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
College Scorecard โ 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.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
County Presidential Returns 2000-2024 (MIT MEDSL). Vote shares, party trends, turnout by countyfips (joins census/education data). Requires HARVARDDATAVERSEAPIKEY. Critical: mode='TOTAL' drops 1K counties post-2020 โ use 3-pattern reconstruction.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Spatial data: GeoDataFrames, spatial joins, CRS/projections, choropleth/interactive maps, spatial autocorrelation, PySAL. Use for geographic data, spatial files (Shapefile, GeoPackage, GeoParquet), or spatial stats. For charts without GIS use plotly.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Panel data, IV/GMM, system regression. PanelOLS (FE/RE), BetweenOLS, Fama-MacBeth, IV2SLS/LIML/GMM, SUR, 3SLS, Driscoll-Kraay SEs. Use for RE/between, system estimation, or GMM. Complements pyfixest (FE + DiD) and statsmodels (GLM + time series).
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Reactive Python notebook system. Cell reactivity, UI elements (sliders, dropdowns, tables), SQL cells, plotting, app deployment. Use when assembling Stage 9 notebooks, building data apps, or converting Jupyter to marimo .py format.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Plotly interactive visualization. Express and Graph Objects: scatter, line, bar, heatmap, 3D, geographic charts; subplots; styling; export. Use when interactivity (hover/zoom) is needed. For static figures use plotnine; for GIS use geopandas.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Skill "plotnine" from brycewang-stanford/Auto-Empirical-Research-Skills, covering plotnine skill, what is plotnine?, how to use this skill, reference file structure and quick decision trees.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Polars DataFrame library for high-performance data manipulation. Lazy/eager execution, expressions, I/O (CSV, Parquet, JSON), aggregations, joins, string/datetime ops, pandas interop. Use for Polars DataFrames or reading/writing Parquet files.
brycewang-stanford/Auto-Empirical-Research-Skills
Skill Claude CodeCodex
Fast high-dimensional fixed effects: OLS, Poisson, IV with multi-way FE; DiD (TWFE, did2s, Sun-Abraham); clustered SEs; etable/coefplot/iplot. Use for FE regressions or DiD. For panel RE/between use linearmodels; for GLM without FE use statsmodels.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page โ the rest are on their repository pages: