vc-setup

What problem does it solve? Setting up an AI agent development harness requires detecting the project stack, creating process directories, and writing real project context — a tedious manual process that often produces stale placeholder docs. This Skill automates detection, scaffolding, deep codebase study, and validation while always asking before reorganizing existing files. ## Core Features & Use Cases - Interactive Detection and Classification: Detects package manager, framework, test runner, and monorepo structure across JS, Python, Go, Ruby, and Rust projects, then classifies the repo as new or existing to pick the right setup flow. - Scaffold with Safe Migration: Creates the process/ directory tree from seed templates and migrates legacy layouts (old plans/, reports/, skills/ dirs) using safe-inference rules, never overwriting user content without approval. - Deep STUDY Phase: Spawns parallel subagents to scan architecture, tests, context groups, and feature areas, then populates all-context.md and all-tests.md with real researched content instead of placeholders. - Use Case: You just cloned a Kotlin Multiplatform repo and want an agent harness. Run the setup, answer a few discovery questions, and receive a fully populated process/ directory with validated context files and feature folders. ## Quick Start Ask the agent to run vc-setup to detect this project's stack and scaffold the agent harness with populated context files.