agent toolingby brycewang-stanford
Setup and Verification
brycewang-stanford/stata-setup
Install, configure, update, or verify mcp-stata across Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and VS Code.
What it changes
Passed 16 of 20 test cases with the skill, and 11 of 20 without it.
Without skill55%
With skill82%
Checks it passed that the model alone missed
- Checks uv CLI tool availability
- Checks uvx CLI tool availability
- Identifies mcp-stata as the server id
and 5 more in the full report
7 fixed11 passed either way3 still failing1 broke
- Pass-rate lift
- +27 pp
- Tokens
- -36%
- Agent turns
- 0%
- Response time
- -63%
Model gemini-3.6-flashMeasured 8/9/2026v118 of 22 cases passed with skill · 20 comparable
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptIf no version flag is passed to the setup script during installation, what release version does it select by default?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Installs the latest version by default | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md70 linessingle file
Setup and Verification
Use the shared installer and verification flow instead of hand-writing per-agent config unless the user explicitly asks for manual steps.
Preferred Install Commands
Project-shared install:
bash plugin/install.sh --scope project
Personal install:
bash plugin/install.sh --scope user
Specific agent:
bash plugin/install.sh --agent codex
Pin a version if a lab wants to:
bash plugin/install.sh --version 2.5.1
Offline/local source:
bash plugin/install.sh --local-source /path/to/mcp-stata
Live verification:
bash plugin/install.sh --verify
Track record
Benchmark
16 / 20
test cases passed, vs 11 / 20 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-setup/SKILL.md
License NOASSERTIONImported 8/2/2026Version v1