Refactoring a Repo to agenteq

1. What this produces

The end state matches what npx agenteq init produces on a repo with no existing AI configuration.

• A canonical source directory, default .ai: GUIDELINES.md, mcp/<name>/config.json, commands/**, skills/**.
• An agenteq.json file recording the chosen agents and capabilities.
• Every generated per-agent file (CLAUDE.md, .cursor/skills, .mcp.json, and so on) gitignored.
• No generated file left tracked in git.

Nothing under the canonical source directory is generated. It is the source every agent file comes from. This skill's job is to get real, scattered content into that directory without losing any of it, then hand off to agenteq's own CLI to generate the rest.

2. Ask for the source directory

Ask the user for the canonical source directory. Default: .ai (agenteq's DEFAULT_SOURCE_DIR). Use their answer for every path below.

If that directory already has content, treat it as the current canonical state. Merge new findings into it. Do not overwrite it.