Passed 16 of 23 test cases with the skill, and 7 of 23 without it.
Without skill32%
With skill68%
Checks it passed that the model alone missed
Mentions running eda.py via uv run.
Specifies EDA_URL as a required environment variable.
Starts with listing activations using list_activations.
and 9 more in the full report
10 fixed7 passed either way7 still failing1 broke
Pass-rate lift
+36 pp
Tokens
-4%
Agent turns
0%
Response time
-59%
Model gemini-3.6-flashMeasured 8/16/2026v117 of 25 cases passed with skill · 23 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
We need to register a new container image containing custom collections and Python dependencies for running EDA rulebooks. Instead of building the container manually or running podman commands, which tool should we execute?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends create_decision_environment for registering new container images.
Missed
Passed
case-08 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.