Automated pipeline that takes a company name and produces a custom Tessl skill plus an eval report showing per-scenario lift (baseline agent vs with-skill agent). A1 MVP cell of the produce/consume × personalization 2x2.
88
86%
Does it follow best practices?
Impact
89%
1.45xAverage score across 13 eval scenarios
Advisory
Suggest reviewing before use
The marketing ops team is gearing up for a developer conference and exported the registration list into inputs/attendees.csv. They want a full A1 batch run completed before tomorrow morning so the booth reps can pull per-company artifacts as visitors arrive.
Run the batch-driver skill against inputs/attendees.csv. Document the command you ran and its outcome in summary-log.txt for the team's morning standup.
summary-log.txt documenting the command(s) run, the parse summary, and the disposition of the batch.runs/<DISCOVERY_RUN_TS>/.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
skills
batch-driver
build-and-evaluate
company-list-filter
discovery
discovery-produce
select-target