Diagnose local Stata, MCP, package, startup, graph-export, and permissions issues.
SkillScore23Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/9/2026
What it changes
Passed 3 of 14 test cases with the skill, and 2 of 14 without it.
Without skill14%
With skill23%
Checks it passed that the model alone missed
Defers recommending fixes until logs and environment reporting are completed.
Instructs running scripts/report_environment.py to gather kernel and environment metrics.
Requires gathering package checks and environment reports before proposing module updates.
and 3 more in the full report
3 fixed2 passed either way16 still failing1 broke
Pass-rate lift
+9 pp
Tokens
+3%
Agent turns
0%
Response time
0%
Model gemini-3.6-flashMeasured 8/9/2026v15 of 22 cases passed with skill · 14 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
My Docker container running Stata MP fails during startup with a missing license initialization error. I want to jump straight to mounting a new stata.lic file in the container. What diagnostic procedure should I follow first?
What was checked, without and with the skill
Checked
Without skill
With skill
Calls for running scripts/report_environment.py to obtain an environment summary before replacing license files.
Missed
Passed
Defers recommending fixes until logs and environment reporting are completed.
Missed
Passed
case-05 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md10 lines3 filesincludes scripts
Environment Diagnose
Use this skill for setup and platform troubleshooting.
Verify detection with stata_manage_session(action="detect").
Reproduce the smallest failing command.
Use logs, package checks, and environment reporting before suggesting a fix.
Separate root cause, evidence, remediation, and verification.
Read references/troubleshooting.md for the diagnosis flow and use scripts/report_environment.py for a deterministic environment summary.