trainer-train-skill

name	trainer-train-skill
description	Own the end-to-end trainer loop for agent skill targets (SKILL.md files and their supporting references, scripts, and evals). Use this whenever the caller needs to research, synthesize datasets, optimize, validate, and write back a trained candidate for a skill-type target. Prefer this specialized loop whenever the selected target is a SKILL.md file or the user wants to improve skill triggering accuracy, body content quality, or progressive-disclosure structure.
argument-hint	Describe the skill directory, the repository root, the validation command, the available stage capabilities, the improvement focus (frontmatter, body, structure, or all), and any existing workspace artifacts.
license	MIT
compatibility	Python 3.11+. Designed for repositories following the agentskills.io specification. Works with skills that keep trainer artifacts in `.trainer-workspace/` next to the selected target.
metadata	{"author":"Tyler Kendrick","version":"0.1.0"}

Trainer Train - Skill

Use this skill as the orchestration contract for one trainer run against an : a file and its associated directory of references, scripts, assets, and evals.