education-data-explorer
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 — discovery here, download there.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-explorer --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Discovers available education data from the Urban Institute Education Data Portal: endpoints, variables, year coverage, and join keys for schools, districts, and colleges (CCD, IPEDS, CRDC, College Scorecard, SAIPE, and more). Use during discovery and scoping phases when identifying what data exists, mapping research questions to endpoints, or resolving variable name discrepancies between documentation and actual field names.
How it works
- Identifies data levels (schools, school-districts, college-university) and data sources (CCD, IPEDS, CRDC, EDFacts, SAIPE, FSA, MEPS, PSEO, etc.).
- Provides reference files and quick reference tables for endpoints, variables, and years, guiding users to the correct endpoints and variable mappings.
- Suggests loading deeper context with source-specific skills when necessary, and using the education-data-query skill for downloads after discovery.
- Indicates that year coverage and mirroring patterns vary by source and that some endpoints support programmatic metadata discovery via a metadata API.
- Includes guidance on planning queries and planning data usage across data levels and sources.
When to use it
- During discovery and scoping phases to identify available data and how research questions map to endpoints and variables.
- When resolving variable name discrepancies between documentation and actual API fields.
- When planning query construction and understanding which data sources to consult for a given topic.
What it can touch
- Education Data Portal endpoints and variables across CCD, IPEDS, CRDC, EDFacts, SAIPE, College Scorecard, MEPS, FSA, NHGIS, and more.
- Endpoints and variable lists referenced in the skill's reference files and data source mappings.
Caveats
- Coverage varies by source; some datasets may be fully mirrored while others are partially mirrored with subset variables.
- Variable names in API responses may differ from documentation; test queries are recommended to confirm actual column names.
- This skill is for discovery and planning; actual data download is handled by the education-data-query skill after discovery.
# Education Data Explorer Discovers available education data from the Urban Institute Education Data Portal: endpoints, variables, year coverage, and join keys for schools, districts, and colleges (CCD, IPEDS, CRDC, Scorecard, SAIPE, and more). Use during discovery and scoping phases when identifying what data exists, mapping research questions to endpoints, or resolving variable name discrepancie
What does the education-data-explorer skill do?
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 — discovery here, download there.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-explorer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.