Passed 18 of 25 test cases with the skill, and 7 of 25 without it.
Without skill27%
With skill73%
Checks it passed that the model alone missed
Includes the header `## Results`.
Includes the header `## Recommendations`.
Includes a section header titled `## Results`.
and 5 more in the full report
21 fixed1 passed either way0 still failing3 broke
Pass-rate lift
+45 pp
Tokens
+29%
Agent turns
0%
Response time
+18%
Model gemini-3.6-flashMeasured 8/24/2026v122 of 25 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 21 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 21
Prompt
Customer Success Manager Rachel achieved 105% net retention, $50k expansion ARR, and 12 quarterly reviews. Team average is 100% net retention, $30k expansion ARR, and 15 reviews. Create a rep performance scorecard with peer comparison and development recommendations.
What was checked, without and with the skill
Checked
Without skill
With skill
Includes the header `## Recommendations`.
Missed
Passed
Recommends increasing quarterly review cadence toward team benchmark.
Passed
Passed
case-14 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.