eval-author-task-create

Propose dataset improvements from Eval Author audit findings, then optionally create one Harbor task from one actionable uncovered tool. Prove the task with Harbor's Oracle, run it repeatedly with the repository's real agent when authorized, and accept it only when measured ATIF closes the selected gap every time. Use when the user asks to suggest dataset changes, fill an eval gap, turn audit uncovered_items into a Harbor task, or add missing tool coverage. Writes proposals, drafts, and measurements only under `.eval-author/`.