motiful

Repo Scaffold — AI skill for Claude Code

AI community

Project workspace scaffolding for AI-driven development.

How to install Repo Scaffold

This entry records only its repository, not the path inside it, so there is no exact command to give. Open motiful/repo-scaffold and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Repo Scaffold does

Project workspace scaffolding for AI-driven development. Pick an archetype (public split-repo or private monorepo), get the right structure with AI configuration, backstage separation, and skill organization built in.

Alternatives in AI

  • Cc Mini — Ultra-light Harness scaffolding for AI agents, a mini version of claude code 825 ★
  • Mex — Persistent project memory for AI coding agents 672 ★
  • Pebrel — AI-native, GPU-accelerated terminal emulator for Windows with SSH, persistent sessions, split panes, and first 670 ★

README

repo-scaffold

Stop guessing your project layout. Pick an archetype, get the right repo structure.

[![License: MIT][license-shield]][license-url] [![Version][version-shield]][version-url] [![Agent Skills][skills-shield]][skills-url]


[Agent Skills](https://agentskills.io) compatible — works with Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, and other Agent Skills adopters.


The Problem

You're building a project with AI. You need design documents, research notes, roadmaps, and progress tracking — but where do they go?

If you're open-source, private thinking doesn't belong in the public repo. If you're running a monorepo, you still need clean AI configuration and skill organization. If you have distributable skills, each one needs its own repo for `npx skills add`. Getting this wrong means either exposing private strategy or over-engineering your structure.

Features

  • Two project archetypes — public open-source (split repos) or private monorepo, each with a purpose-built directory layout
  • Local folder = GitHub repo name — backstage uses -backstage/, not generic backstage/. No mental translation, no name collisions across projects
  • AI-native configuration — generates CLAUDE.md (public identity), CLAUDE.local.md (gitignored bridge to private docs), and progress tracking out of the box
  • Skill-aware organization — guides where to place in-repo skills, product skills, rule-skills, and standalone distributable skills
  • Multi-platform support — generates plat