comment-initlisted

Initialize or refresh a repo for the `comment-*` skill family. Two layers: (1) the **repo config the skills read** — the `AGENTS.md`/`CLAUDE.md` "Agent Skill Config" pointer plus `docs/DELIVERY.md` (topology, bounded review, and receipts) and `docs/TESTING.md` (focused iteration and final certification), inferred from the repo's build/test setup; and (2) the **architecture docs as comms** — one living "Architecture Overview" comm plus immutable per-decision ADRs in a Team Wiki folder. Idempotent — re-running reconciles existing files/comms instead of duplicating them. Trigger on "set up comment-init / the comment skills for this repo", "set up the testing config", "set up the architecture doc", "get my architecture", "document the architecture", "write an ADR", or "update the architecture overview". Works identically under Codex and Claude Code.
comment-hq/skills · ★ 0 · Data & Documents · score 72

Install: claude install-skill comment-hq/skills

# comment-init — initialize a repo for the comment-* skills `comment-init` makes a repo ready for the rest of the family (`comment-dev`, `comment-feature`, `comment-bug`, `comment-spec`, `comment-prototype`, `ship`, `review-loop`) by producing and maintaining two layers: 1. **Repo config (on disk, in the repo)** — the files those skills read to learn *this* repo, so they stay generic and don't hardcode commands: - the **Agent Skill Config** pointer in **`AGENTS.md` (else `CLAUDE.md`)**; - **`docs/DELIVERY.md`** — direct/lift topology, bounded review receipts, pragmatic completion, and promotion rules; and - **`docs/TESTING.md`** — focused and final-candidate lanes. 2. **Architecture docs (as Comment.io comms)**: - **Architecture Overview** — ONE living comm: *what is true now* (system overview, component boundaries, data flows, a Mermaid diagram, invariants). Re-running reconciles this same comm; it is never duplicated. - **Architecture Decision Records (ADRs)** — IMMUTABLE comms, one per decision, in a **Team Wiki folder**. An ADR records *why*; reversing a decision means a *new* ADR that supersedes the old one. The Overview's invariants link to the ADRs that justify them. Run the **Repo config** layer first when setting a repo up for the skills; run the **Architecture** layer to document or refresh how the system is built. Either can run alone. ## When to use - **First-time setup** of a repo for the `comment-*` skills → r