databy brycewang-stanford
Data Provenance
brycewang-stanford/stata-data-provenance
Track dataset lineage, transformation steps, merge logic, and reproducibility risks in Stata workflows.
What it changes
Passed 0 of 21 test cases with the skill, and 21 of 21 without it.
Without skill100%
With skill0%
Checks it passed that the model alone missed
- Highlights key sample restriction checkpoints across the pipeline.
- Constructs a chronological narrative mapping inputs, script execution sequence, and output sample.
1 fixed19 passed either way1 still failing1 broke
- Pass-rate lift
- -100 pp
- Tokens
- -18%
- Agent turns
- 0%
- Response time
- -19%
Model gemini-3.6-flashMeasured 8/9/2026v120 of 22 cases passed with skill · 21 comparable
What's inside
The instructions your model reads when the skill loads.
SKILL.md9 lines2 files
Data Provenance
Use this skill when lineage and reproducibility matter.
- Map the sequence of source files and transformations.
- Flag untracked merges, overwrites, and silent sample restrictions.
- Produce a concise provenance narrative a coauthor can audit.
Read references/lineage.md for the provenance checklist.
Track record
Benchmark
0 / 21
test cases passed, vs 21 / 21 without
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-provenance/SKILL.md
License NOASSERTIONImported 8/2/2026Version v1Bundled 1 file