ralph-kage-bunshin-start
/ralph-kage-bunshin-start — Ralph Project Setup Skill
You are setting up a new Ralph project. Run a structured, dimension-based interview to fully understand what the user wants to build — then synthesize a tight spec and granular task list.
Phase 0: Context Detection
Before asking anything, explore the environment:
- Check if cwd has existing source files,
package.json, or git history → brownfield or greenfield - Check
CLAUDE.mdif present
If .ralph/SPEC.md already exists:
"A spec already exists for this project. Resume from where you left off, or start over?"
- Resume: read the existing SPEC.md and tasks.json, then pick up from the first incomplete dimension
- Start over: confirm before deleting — "This will overwrite the existing spec. Are you sure?"
UI Clone Detection (before interview)
If the user provides a URL and mentions cloning/copying/replicating a site:
More from dididy/ralph-kage-bunshin
ralph-kage-bunshin-debug
Use when a ralph worker has 3+ consecutive failures and needs diagnosis — reads error output and code to find root cause with file:line evidence, proposes ONE fix (does not implement it), writes debug_session to state.json and reports to watcher
2ralph-kage-bunshin-loop
Worker execution loop for ralph-kage-bunshin — receives a task assignment, implements via TDD, runs DoD verification, and reports results to the watcher. Invoked by the watcher, not manually.
2ralph-kage-bunshin-verify
Use to independently validate a ralph worker's completed task without changing state — re-runs tests and build, checks each acceptance criterion and E2E scenario, returns PASS/FAIL/INCOMPLETE verdict. Read-only; does not write to state.json or tasks.json (use /ralph-kage-bunshin-architect to approve/reject).
2ralph-kage-bunshin-architect
Review and approve/reject a ralph worker's completed task — checks spec compliance, code correctness, E2E coverage, steelmans before approving, and reports verdict to the watcher via fakechat. This is the approval authority; use /ralph-kage-bunshin-verify for read-only checks without state changes.
2api-integration-checklist
Use before implementing any external API integration — verifies endpoints against live API, checks CORS support, auth/security requirements, rate limits, pagination, timeout, caching, and decides whether a proxy layer is needed. Run at design time to catch integration blockers before coding.
2ralph-kage-bunshin-watcher
Central orchestrator for ralph-kage-bunshin — manages task assignment, worker lifecycle, architect/debugger spawning, and health monitoring. Invoked automatically by `ralph team`, not manually.
1