Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit datasets for structure, missingness, labeling, suspicious values, duplicate identifiers, and documentation readiness. Use when a researcher asks for data QA, codebook review, sanity checks, or pre-analysis cleanup guidance.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -81% | 0% |
| case-07 | ✓→✗ | ▼ Worse | -76% | 0% |
| case-08 | ✓→✗ | ▼ Worse | -49% | 0% |
| case-10 | ✓→✗ | ▼ Worse | -73% | 0% |
Run a compact but explicit audit of the active dataset.
stata_inspect_data(action="describe") and stata_inspect_data(action="summary").codebook, search, and stata_run checks for key variables or suspicious patterns.Read references/checklist.md for the full audit checklist and recommended output format.
Other measured skills in the registry, with their headline benchmark lift.