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
Your team is preparing for a developer summit and a coworker exported the attendee list from the conference registration system into inputs/companies.txt. They were in a hurry and want you to run the standard pre-discovery triage so the discovery pipeline can pick up the survivors first thing tomorrow.
If the export yields a usable list of unique companies, produce triage-report.md with the four-section classification and dedup-output.json containing the deduplication output.
If the export is unusable, write triage-skipped.md documenting what you read, what the deduplication step returned, and what the coworker should do to re-export the file.
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