first-tree-seedlisted

One-time bootstrap for a brand-new, still-empty Context Tree. Delivers an initial top + second-level domain skeleton drawn from the bound source repos (PR1, user approves), then initial leaf-node content for each approved domain with explicit coverage reporting (PR2). Use right after Cloud onboarding provisions the workspace and tree repo. Refuses on any populated tree. Do not use to write an incremental update from a specific PR / doc / note — that is `first-tree-context`. Do not use to audit drift on an existing tree — that is `first-tree-sync`.
agent-team-foundation/first-tree · ★ 18 · AI & Automation · score 77

Install: claude install-skill agent-team-foundation/first-tree

# First Tree — Seed Read this skill **before** drafting the first content into a freshly provisioned Context Tree. It owns the one-time bootstrap from "Cloud just gave me an empty tree repo" to "the tree has real top + second level structure plus initial leaf nodes drawn from the bound source repos". Every subsequent write — one PR at a time, one decision at a time — belongs to `first-tree-context`, not here. ## When To Use This Skill | Use `first-tree-seed` | Use a different skill | | --------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | | Cloud onboarding finished; the tree repo is empty (no top-level dirs) | The tree already has a domain structure → `first-tree-context` (incremental write) | | First content pass on the bound sources | Audit drift between merged code and an existing tree → `first-tree-sync` | | Invoked by name — by a human, or by a future kickoff prompt once Cloud provisions before sending (see Trigger) | Workspace is unbound → surface to a human (binding is a web-console operator action, not an agent's) | The skill is **single-shot per tree**. If a previous seed already landed (PR1 merged), do not re-run; route any further work throug