Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Brycewang Stanford/Stata Lint — measured AI agent skill | DecimalAI

brycewang-stanford/stata-lint

NewSkillScoreMaintained

Run static analysis on a Stata .do or .ado file and report style and best-practice issues.

Code Reviewby brycewang-stanford

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull brycewang-stanford-stata-lint

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/brycewang-stanford-stata-lint/SKILL.md

Raw file: /s/brycewang-stanford-stata-lint/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-stata-lint.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

25 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9h ago

—-36% tokens0% turns44% of whole cases pass with skill (11/25)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-19%	0%
case-17	✗→✓	▲ Improved	-39%	0%
case-18	✗→✓	▲ Improved	-73%	0%
case-11	✓→✗	▼ Worse	-29%	0%
case-13	✓→✗	▼ Worse	-74%	0%

Showing 5 of 25 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

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

Imported

brycewang-stanford / Auto-Empirical-Research-Skills

skills/64-tmonk-mcp-stata/skills/stata-lint/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

Skill contents

SKILL.md

The argument is the absolute path to a .do or .ado file.

Call stata_inspect_data(action="lint", path=<argument>).

Display the lint results, grouping issues by severity or type:

Line number and issue description for each finding
Common issues: use of cd, preserve/restore, #delimit, hardcoded paths, long lines, missing version statement

For each category of issue found, briefly explain the modern alternative (refer to the stata-modernize skill for details).

If the file is clean, confirm: "No issues found in <filename>."

If the path argument is missing, tell the user to provide an absolute path to a .do or .ado file.

Want to see if brycewang-stanford/stata-lint would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.