Generate eval scenarios from repo commits, configure multi-agent runs, execute baseline + with-context evals, and compare results — the full setup pipeline before improvement begins
Overall
score
90%
Does it follow best practices?
Validation for skill structure
The user says: "I just ran tessl scenario generate acme/backend --commits=f9256db,a13eb72 --workspace=myteam and it finished. The output showed two Scenario IDs. Now I want to download all the scenarios so I can review them before running. How do I do that?"
Help the user download their generated scenarios correctly.