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 skill-discovery platform maintains a queue of companies to process. Today's queue has two entries:
Company slug: acme-corp — The platform stores run history under inputs/runs/<UTC-timestamp>/acme-corp/. Multiple runs may exist; you need the right one.
Explicit path: inputs/beta-inc/selection.json — A pre-identified selection file for Beta Inc.
Before the pipeline can scaffold and evaluate a skill for any company, it must validate whether the selection is ready to proceed. If a company is not ready, the pipeline should stop gracefully for that entry and explain why. If it is ready, the pipeline should load all necessary context and determine what the first build command would be.
Write a run-log.md documenting what happened for each company:
tessl skill new) would look like with the correct --path argumentProduce run-log.md with a section for each company in the queue. For companies where processing proceeds, include the full tessl skill new command with all required flags filled in from the discovered context.
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