wrote write-the-changelog.eval.yaml, write-the-changelog.task.md (1 case)
mapped:   task -> prompt_file
mapped:   6 criteria -> rubric (weights kept as text)
assumed:  no pass threshold; the eval default 0.70 applies
assumed:  expect_trigger: true (the scenario targets a skill)
assumed:  lifted contains and not_contains assertions match case-sensitively; the criteria they came from do not say so
lifted:   criterion "file exists" -> file_exists "CHANGELOG.md"
lifted:   criterion "mentions version" -> contains "2.0.0"
lifted:   criterion "no draft marker" -> not_contains "DRAFT"
lifted:   criterion "no tmp file" -> file_exists "notes.tmp" (absent)
