Passed 7 of 15 test cases with the skill, and 8 of 15 without it.
Without skill52%
With skill44%
Checks it passed that the model alone missed
Defines a REST connection with class rest and protocol https.
Declines to execute POST, PUT, or PATCH configuration changes.
Sets CPU utilization greater than 80% as a health warning threshold.
and 7 more in the full report
5 fixed6 passed either way7 still failing7 broke
Pass-rate lift
-8 pp
Tokens
+361%
Agent turns
0%
Response time
-37%
Model gemini-3.6-flashMeasured 8/16/2026v111 of 25 cases passed with skill · 15 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
Construct a pyATS YAML testbed definition for BIG-IP load balancer bigip-01 at 10.0.0.20 to enable iControl REST interaction over HTTPS on port 443 with environment variable credentials.
What was checked, without and with the skill
Checked
Without skill
With skill
Configures the target device operating system as bigip.
Passed
Passed
Defines a REST connection with class rest and protocol https.
Missed
Passed
Uses environment variable substitutions %ENV{F5_USERNAME} and %ENV{F5_PASSWORD} for default credentials.
Missed
Passed
case-11 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.