Arvore Repo Hub

Roadmap

What Works Today

  • Core concept — The gitignore/cursorignore pattern for cross-repo AI context
  • Config formats — hub.yaml (YAML) and hub.config.ts (TypeScript with type-safe helpers via defineConfig, repo, mcp, service)
  • Interactive TUI — hub init launches a multi-step wizard with editor selection, repo setup, skill selection from the directory registry, MCP picking, and config format choice
  • CLI commands — init, add-repo, setup, generate, env, services, tools, skills, registry, pull, status, exec, worktree, doctor
  • Generator targets — Cursor (.cursor/rules/, .cursor/mcp.json), Claude Code (CLAUDE.md), Kiro (.kiro/steering/, .kiro/settings/mcp.json), OpenCode (opencode.json, .opencode/), AGENTS.md
  • Skills system — Capabilities (refinement, code-review, qa-testing, debugging, per-stack skills) the AI pulls on demand; install from git repos, project and global scopes, per-repo assignment
  • On-demand subagents — Spawn a fresh-context subagent that pulls the relevant skill when an independent pass helps (e.g. unbiased review), via the editor’s native subagent mechanism
  • Tool management — Declare versions in hub.yaml, generate .mise.toml, install via mise
  • Environment management — Profiles, AWS Secrets Manager, per-repo overrides, per-repo profile override, DATABASE_URL building
  • Docker services — Generate docker-compose.yml, manage lifecycle (up/down/logs/clean)
  • Worktrees — Create parallel workspaces with env file copying
  • MCP servers — 7 open-source MCPs (MySQL, PostgreSQL, AWS Secrets, Datadog, npm registry, tempmail, Playwright)

Short Term

  • Hub registry — Community hub for browsing and installing skills and capability libraries
  • Windsurf adapter — generate --editor windsurf
  • Copilot Workspace adapter — generate --editor copilot

Medium Term

  • Skill usage insights — Which skills get pulled, where they help, and where coverage is missing
  • Multi-hub — Compose multiple hubs (platform team + feature team)
  • Plugin system — Third-party generators, MCP wrappers, custom capabilities

Long Term

  • Self-improving skills — The AI proposes skill updates based on recurring patterns
  • Cross-team orchestration — Hub-to-hub communication for platform/product split

How to Contribute

Pick any area and open a PR. For larger items, open an issue first to discuss approach.

Easiest high-impact contributions:

  1. Editor adapters — Windsurf, Copilot Workspace, or any AI editor
  2. Skills — Write a SKILL.md for your framework/language (Go, Python/Django, Java/Spring, Vue, Svelte) or a cross-cutting capability
  3. Skill improvements — Sharper guidance, better triggers, broader coverage
  4. Documentation — Guides, tutorials, videos