Stats
Actions
Tags
From kagura-engineer
Use to bootstrap a fresh checkout for the kagura-engineer harness — scaffolds a commented repo.yaml template and adds it to .gitignore by shelling out to `kagura-engineer init`. Run this before setup/run/review when no repo.yaml exists yet. Idempotent and never overwrites.
How this skill is triggered — by the user, by Claude, or both
Slash command
/kagura-engineer:initThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Thin wrapper around the `kagura-engineer init` CLI verb. It scaffolds the per-checkout
Thin wrapper around the kagura-engineer init CLI verb. It scaffolds the per-checkout
repo.yaml template and adds it to .gitignore so the workspace/context IDs never land
in git. It reimplements nothing — it shells out to the installed CLI and surfaces the result.
Announce: "Using the kagura-engineer:init skill to scaffold repo.yaml."
Safe to run anytime: it is idempotent and never overwrites an existing
repo.yaml. No repo mutation beyond writingrepo.yaml(if absent) and appending one line to.gitignore. Not a Harness — no model budget, no PR, no HITL gate.
Usage: kagura-engineer:init — no arguments. Add --dir <path> to scaffold a repo other
than the current directory.
Run init:
kagura-engineer init
Pass --dir <path> to scaffold a different repo root (default: current directory).
Surface the result. Report whether repo.yaml was created (or left unchanged
because it already existed) and whether repo.yaml was added to .gitignore.
Hand off. Tell the user to edit repo.yaml (profile, backend choice,
workspace/context ids), then run kagura-engineer:setup to provision the environment
and kagura-engineer:doctor to verify it.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub kagura-ai/kagura-engineer --plugin kagura-engineer