ralph-deploylisted

Plan and configure ralph-orchestrator deployments for projects at any stage — from a vague phase plan to a mature codebase. Use this skill whenever the user wants to set up ralph for a new project, choose between deployment topologies (direct, Claude+MCP, multi-project supervisor), pick the right config for their project's maturity, run oneshot autonomous builds, or manage multiple concurrent ralph loops across tmux sessions. Also use when the user asks "how should I run ralph on this?", mentions phase plans, or wants to configure cost budgets, hat workflows, or guardrails for a specific project type.
bayeslearner/bayeslearner-skills · ★ 0 · AI & Automation · score 62

Install: claude install-skill bayeslearner/bayeslearner-skills

# Ralph Deploy Configure and launch ralph-orchestrator. Install: `cargo install --git https://github.com/mikeyobrien/ralph-orchestrator ralph-cli` ## Directory Discipline ``` .kiro/specs/ # specs (committed) NN-<name>/ requirements.md # input: the spec AND the ralph prompt (-P) design.md # output: archived scratchpad after loop progress.txt # output: timestamped task log steering/ # optional: product vision, tech decisions .ralph/ # orchestrator (gitignored runtime state) ralph.yml # config (core.specs_dir → .kiro/specs) hats/greenfield.yml # hat definitions with ceremony instructions agent/scratchpad.md # hat handoff channel (ephemeral) agent/memories.md # persistent constraints (seed with ceremony rules) ``` **Rules:** No root pollution. requirements.md IS the prompt — no separate prompt.md. design.md is an output, not an input. `.kiro/specs/` is canonical — migrate legacy locations. Number spec dirs sequentially (`01-`, `02-`). ## Before You Start ```bash ralph loops list # existing loops? tmux has-session -t ralph-$NAME 2>/dev/null && echo "running" ls .ralph/loop.lock 2>/dev/null # stale lock? ``` If running: monitor, don't start another. If stale lock with no session: `rm .ralph/loop.lock`. ## Hats = Roles in the Loop