databy brycewang-stanford
Data Audit
brycewang-stanford/stata-data-audit
Audit datasets for structure, missingness, labeling, suspicious values, duplicate identifiers, and documentation readiness.
What it changes
5 of 22 test cases passed with the skill.
- Pass-rate lift
- —
- Tokens
- -36%
- Agent turns
- 0%
- Response time
- -34%
Model gemini-3.6-flashMeasured 8/11/2026v15 of 22 cases passed with skill · 5 comparable
Lift withheld: 5 comparable cases; this report requires 8.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhere can full detailed audit procedures and recommended output formats for Stata dataset health checks be found in the system reference docs?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| References references/checklist.md for the full audit checklist. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md9 lines2 files
Data Audit
Run a compact but explicit audit of the active dataset.
- Start with
stata_inspect_data(action="describe") and stata_inspect_data(action="summary").
- Use targeted
codebook, search, and stata_run checks for key variables or suspicious patterns.
- Report concrete issues, not generic reassurance.
Read references/checklist.md for the full audit checklist and recommended output format.
Track record
Benchmark
5 / 22
test cases passed with the skill
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedbrycewang-stanford / Auto-Empirical-Research-Skills
skills/64-tmonk-mcp-stata/skills/stata-data-audit/SKILL.md
License NOASSERTIONImported 8/2/2026Version v1Bundled 1 file