repo2skill

name	repo2skill
description	Scaffold, author, and review a new gate-passing Agent Skill for this repo (or any repo vendoring its quality gates): generate a standards-complete skeleton, write the real prompt over it, run the semantic review the mechanical gates cannot, and iterate the gates to green. Use when someone says "create a new skill", "add a skill to agent-skills", "scaffold a SKILL.md", "make my skill pass the gates", or "review this SKILL.md for prompt quality". Not for auditing whether a whole repo is ready for coding agents — use agent-ready-rails; not for fact-checking a codebase's claims — use base-in-reality; not for designing or repairing a single agent loop — use crafting-self-prompting-loops.
license	MIT
compatibility	Requires python3 (stdlib only, offline) plus make and a POSIX shell for the gate loop. Built for this repo's layout — the quality gates under scripts/gates were vendored from this skill — but the scaffolder runs anywhere python3 does.
metadata	{"author":"dhanesh","version":"1.0.0","tags":"agent-skills,skill-authoring,scaffolding,prompting-playbook,quality-gates,code-review"}

repo2skill

The authoring skill this repo's quality gates were vendored from. It turns "I want a new Agent Skill" into a directory that passes make gate-skill — by scaffolding a skeleton that is already green, guiding the real authoring over it, and finishing with the semantic review that mechanical gates cannot perform. Author under gate cover: start green, stay green, and let every red check tell you exactly what to fix.