Passed 9 of 23 test cases with the skill, and 14 of 23 without it.
Without skill60%
With skill40%
Checks it passed that the model alone missed
The output includes the top-level heading '# Territory Planning Optimizer Output'.
The output includes the top-level section heading '# Territory Planning Optimizer Output'.
Standard territory reps are assigned mid-market account clusters based on revenue potential.
and 1 more in the full report
4 fixed15 passed either way1 still failing3 broke
Pass-rate lift
-20 pp
Tokens
+17%
Agent turns
0%
Response time
+17%
Model gemini-3.6-flashMeasured 8/28/2026v119 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
I need to rebalance our enterprise sales territories across North America based on account revenue potential and geographic rep proximity. Please analyze our account list, distribute workload evenly among 8 sales representatives, and provide a structured report featuring a primary title header, generation timestamp, a detailed results section outlining rep assignments, and an actionable recommendations section for rollout.
What was checked, without and with the skill
Checked
Without skill
With skill
The output includes the top-level heading '# Territory Planning Optimizer Output'.
Missed
Passed
The account assignment balances total target revenue across all 8 rep territories.
Passed
Passed
The territory design groups accounts by geographic proximity to minimize rep travel overlap.
Passed
Passed
case-01 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.