Optimize your skills and tiles: review SKILL.md quality, generate eval scenarios, run evals, compare across models, diagnose gaps, and re-run until scores improve.
88
94%
Does it follow best practices?
Impact
88%
1.07xAverage score across 24 eval scenarios
Passed
No known issues
Generate scenarios from the tile:
tessl scenario generate <tile-path> --count=<N>Default to --count=3 for a first run, up to 5 for comprehensive coverage. For example:
tessl scenario generate ./my-tile --count=3The CLI polls until complete (~1–2 minutes per scenario). Capture the run ID from the output — you'll need it for the download step.
"Scenario generation typically takes 1–2 minutes per scenario. I'll wait for it to complete."
After generation completes, the CLI shows the generated scenarios. Summarize for the user:
Ask: "These look good? Want me to download them and proceed, or should I regenerate?"
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
skills
compare-skill-model-performance
optimize-skill-instructions
references
optimize-skill-performance
optimize-skill-performance-and-instructions