trainer-train

name	trainer-train
description	Own the end-to-end trainer loop contract for a prompt-like file, skill contract, or agent contract after the caller has already chosen the concrete stage capabilities. Use this whenever the current agent must set up the local trainer workspace, coordinate stage sequencing, maintain workflow state, manage steering and candidates, recover from manual follow-up mode, and decide whether a trained candidate is safe to write back.
argument-hint	Describe the target file, workspace root, validation command, available stage capabilities, agent roster, and any current blocker such as missing review artifacts, missing datasets, or manual follow-up recovery.
license	MIT
compatibility	Python 3.11+. Works in repositories that keep trainer artifacts in a local `.trainer-workspace/` next to the selected target.
metadata	{"author":"Tyler Kendrick","version":"0.1.0"}

Trainer Train

Use this skill as the orchestration contract for one trainer run against one selected target. Treat the concrete research, synthesis, optimization, and election capabilities as caller-supplied stage implementations. This skill owns the loop behavior, workspace state, steering, validation, and write-back rules around those stages.