communication-style
Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.
This skill should be used only when the user explicitly invokes `$ralph-specum-prototype`, or explicitly asks Ralph Specum in Codex to run, resume, quick-run, or cancel an optional prototype.
$ npx -y skills add tzachbon/smart-ralph --skill ralph-specum-prototype --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ralph-specum-prototypeContext preview
The summary Claude sees to decide when to auto-load this skill.
This skill should be used only when the user explicitly invokes `$ralph-specum-prototype`, or explicitly asks Ralph Specum in Codex to run, resume, quick-run, or cancel an optional prototype.
name: ralph-specum-prototype description: This skill should be used only when the user explicitly invokes `$ralph-specum-prototype`, or explicitly asks Ralph Specum in Codex to run, resume, quick-run, or cancel an optional prototype. metadata: surface: helper action: prototype
Coordinate one optional prototype overlay. Delegate source work to a child agent and keep the main Ralph phase unchanged until the recorded handoff.
Derive `RALPH_CODEX_PLUGIN_ROOT` from this loaded skill: take the directory containing `SKILL.md`, then its parent `skills` directory, then the next parent. Never derive the plugin root from the project working directory.
Read `../../references/prototype-coordinator.md` from this skill directory completely before any prototype mutation. Treat it as the source of truth for direct, suggested, resume, quick, cancel, isolation, review, publication, and handoff behavior.
1. Resolve an explicit path, exact spec name, or `.current-spec` with `"$RALPH_CODEX_PLUGIN_ROOT/scripts/resolve_spec_paths.py"`. Use only the returned `basePath`, `specRoot`, settings, and warnings. 2. Parse one mode: direct by default, suggested with a return phase, resume by ID, quick, or cancel by ID. 3. Reconcile candidate and final records before reserving, resuming, reviewing, or publishing. 4. Use only these mechanics:
5. Spawn internal builders with child-agent tools. Store only the returned `agentId`; wait with `wait_agent` and stop with `interrupt_agent`. Never use `create_thread` or a `threadId` for an internal builder. 6. Keep normal capture, dirty-path transfer, verdict, handoff, deletion, and remote actions under explicit user control. Let quick mode own its bounded choices and continue to design after every terminal outcome.
Finish only after the coordinator contract verifies the immutable final bytes, removes the active entry through the locked helper, applies stale and handoff gates, and reports the local source disposition. Keep every remote pointer pending until the user authorizes that exact remote write.
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.
Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
Core Smart Ralph skill defining common arguments, execution modes, and shared behaviors across all Ralph plugins.
Comprehensive understanding of the spec-kit methodology. Constitution-driven feature development with specify, plan, tasks, and implement phases.
Internal Ralph Specum contract for Codex phase interviews, skill manifests, approval, and delegation gates. Phase coordinators load this skill directly; users…
This skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Specum in Codex to stop execution or…