codingby brycewang-stanford
Modernize Stata
brycewang-stanford/stata-modernize
Improve, modernize, and optimize existing Stata code for performance, portability, and maintainability.
What it changes
Passed 8 of 23 test cases with the skill, and 15 of 23 without it.
Without skill67%
With skill33%
Checks it passed that the model alone missed
- gegen avg_score = rowmean(test1-test20)
1 fixed18 passed either way2 still failing2 broke
- Pass-rate lift
- -33 pp
- Tokens
- -29%
- Agent turns
- 0%
- Response time
- -28%
Model gemini-3.6-flashMeasured 8/9/2026v119 of 23 cases passed with skill
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
PromptImprove the runtime of a Stata script deriving row-wise means across 20 test score variables using 'egen avg_score = rowmean(test1-test20)'.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| gegen avg_score = rowmean(test1-test20) | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md9 lines2 files
Modernize Stata
Use this skill when a user wants stronger Stata code, not just working Stata code.
- Identify the current anti-patterns.
- Recommend or implement modern replacements with clear rationale.
- Favor frames,
reghdfe, gtools, portable paths, and explicit state handling.
Read references/patterns.md for common replacements and examples.
Track record
Benchmark
8 / 23
test cases passed, vs 15 / 23 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-modernize/SKILL.md
License NOASSERTIONImported 8/2/2026Version v1Bundled 1 file