education-data-context
Interpretation guidance for Urban Institute Portal datasets. Coded values (-1/-2/-3), year definitions, grade encoding, suppression, licensing, cross-source joins. Use when interpreting Portal data before analysis. Routes to source-specific skills.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-context --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
Interpretation guidance for Urban Institute Portal datasets, covering coded values (-1/-2/-3) in numeric fields, year definitions (fall vs academic year), grade encoding (e.g., grade = -1 means Pre-K), suppression, licensing under the ODC Attribution License, and cross-source joins. It directs users to route to source-specific deep-dive skills when needed.
How it works
The skill provides context on data provenance and cautions, including:
- Why data context matters (source limitations, meaning of missing values, evolving definitions)
- Data provenance and Portal transformations (renaming variables, re-encoding categoricals, standardizing missing values to -1/-2/-3)
- Reference structure linking quick context notes to deep-dive source skills (CCD, CRDC, IPEDS, Scorecard, EDFacts, etc.)
- Decision trees for choosing appropriate source skills based on endpoints
- Detailed encoding guidance for categorical and numeric fields, including the semantic trap for grade -1 as Pre-K, and the distinction between coded numerics and nulls for various sources
- Handling of missing values (-1/-2/-3) and source-specific patterns (CCD/CRDC/EDFacts vs Scorecard/MEPS/NACUBO vs IPEDS)
- Year definitions (Fall year, cohort-based graduation, etc.)
- Suppression policies and state reporting variation
- A data quality checklist and quick coverage checks
- Citation formats for the Portal data
When to use it
Use when interpreting Portal data before analysis to understand value encodings, year definitions, grade semantics, suppression implications, licensing requirements, and how to join identifiers across sources. Also use to determine which deeper, source-specific skills to load for comprehensive methodological context.
What it can touch
Declared tool: claude-code
Caveats
License: NOASSERTION. The skill emphasizes standard Portal behaviors and source-specific caveats; it notes that data provenance dates in provenance.skill_last_updated should be re-verified when applicable. It warns that definitions and suppression patterns may evolve and suggests re-running data-ingest to re-verify when necessary.
# Education Data Context Data origin, caveats, and interpretation guidance for Urban Institute Education Data Portal datasets. Use when interpreting Portal coded values (-1/-2/-3 missing/not-applicable/suppressed), understanding year definitions (fall vs. academic year), applying correct grade encoding (grade=-1 means Pre-K, not missing), assessing suppression rates, citing data under ODC-By licen
What does the education-data-context skill do?
Interpretation guidance for Urban Institute Portal datasets. Coded values (-1/-2/-3), year definitions, grade encoding, suppression, licensing, cross-source joins. Use when interpreting Portal data before analysis. Routes to source-specific skills.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill education-data-context --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.