{
  "version": "act 2.0.0",
  "slug": "onboarding-map",
  "name": "onboarding-map",
  "description": "Use when onboarding to an unfamiliar codebase \u2014 produces a guided reading order (entry points first, then high-traffic and load-bearing code) annotated with ownership and risk flags.",
  "url": "https://act101.ai/docs/skills/onboarding-map",
  "body_md": "# Onboarding Map\n\nTurn an unfamiliar repository into a guided reading order: where to start, what to read next, and what to be careful around.\n\n## When to use\n\n- A developer (or agent) is new to a codebase and needs a path through it.\n- Building a mental model fast, prioritizing the code that matters.\n\n## Protocol\n\n1. **Shape** \u2014 call `repo_outline` to get the file tree, languages, and sizes. This is the territory.\n2. **Entry points** \u2014 call `analyze_entry_points` to find mains, HTTP routes, CLI commands, and event listeners. These are where execution (and reading) should begin.\n3. **Traffic** \u2014 call `churn_hotspots` (workspace mode) to find the most actively-changed code \u2014 what the team touches daily.\n4. **Ownership** \u2014 call `ownership_map` to find who knows what, and which symbols have a low bus factor (read these carefully; the expert may be unavailable).\n5. **Sequence** \u2014 produce a reading order: entry points \u2192 the high-churn core they reach \u2192 supporting modules. Annotate each step with its owner(s) and a risk flag for low-bus-factor or high-churn code. Keep it short and ordered; this is a path, not a catalog.\n\n## Output\n\nAn ordered reading list. Each step: what to read (file/symbol), why it's next (entry point / high churn / load-bearing), its owner(s), and any risk flag. End with \"areas to be careful around\" (low bus factor, high churn).\n\n## Honesty\n\nOwnership and churn are git facts but degrade to file-level for grammars without symbol extraction (`modeled_kinds`) \u2014 say so. Entry-point and outline data are syntactic."
}