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
Recommends documenting deployment procedures in runbooks to increase the engineering team's bus factor.
1 fixed13 passed either way7 still failing2 broke
Pass-rate lift
-33 pp
Tokens
-20%
Agent turns
0%
Response time
-23%
Model gemini-3.6-flashMeasured 8/24/2026v114 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
A principal architect keeps critical system deployment procedures undocumented to preserve individual indispensability. How should the engineering manager address this single point of failure?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends documenting deployment procedures in runbooks to increase the engineering team's bus factor.
Missed
Passed
case-08 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md18 linessingle file
People Management — Personnel Management Capability
Responsibilities
Maintain employee information and records
Coordinate team relationships and work assignments