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 asks to use `$ralph-specum-refactor`, or explicitly asks Ralph Specum in Codex to revise spec artifacts after implementation learnings.
$ npx -y skills add tzachbon/smart-ralph --skill ralph-specum-refactor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ralph-specum-refactorContext preview
The summary Claude sees to decide when to auto-load this skill.
This skill should be used only when the user explicitly asks to use `$ralph-specum-refactor`, or explicitly asks Ralph Specum in Codex to revise spec artifacts after implementation learnings.
name: ralph-specum-refactor description: This skill should be used only when the user explicitly asks to use `$ralph-specum-refactor`, or explicitly asks Ralph Specum in Codex to revise spec artifacts after implementation learnings. metadata: surface: helper action: refactor
You are a **coordinator, not a refactor specialist** -- delegate spec revision to a `refactor-specialist` sub-agent.
1. Resolve the target spec. 2. Read `.progress.md` and existing spec files. 3. Run `prototype_records.py reconcile` whenever `.ralph-state.json` exists, including when `activePrototypes` is empty, then run `select-downstream --state "$BASE_PATH/.ralph-state.json" --target "$FILE" --path "$FILE"` with the resolved `basePath`. Stop a file's refactor when its `targetDecisions` entry is not both `proofAvailable: true` and `eligible: true`, including an active blocker, stale dependency, approved-transfer overlap, or unavailable proof. 4. When refactor returns to execution, restore `taskIndex` from the blocking entry's `returnTaskIndex` through `merge_state.py` before dispatch. 5. **Delegate** spec revision to a `refactor-specialist` sub-agent. Pass `.progress.md`, existing spec files, and implementation learnings. The sub-agent identifies what changed, what stayed accurate, and what is obsolete. Do NOT revise spec files yourself. 6. The sub-agent preserves newer Ralph concepts already expressed in the spec, including approval checkpoints, granularity choices, `[P]` tasks, `[VERIFY]` tasks, VE tasks, and epic constraints when relevant. 7. The sub-agent updates files in order:
8. If requirements changed, revisit design and tasks. 9. If design changed, revisit tasks. 10. Record the rationale and cascade decisions in `.progress.md`.
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.
Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
Core Smart Ralph skill defining common arguments, execution modes, and shared behaviors across all Ralph plugins.
Comprehensive understanding of the spec-kit methodology. Constitution-driven feature development with specify, plan, tasks, and implement phases.
Internal Ralph Specum contract for Codex phase interviews, skill manifests, approval, and delegation gates. Phase coordinators load this skill directly; users…
This skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Specum in Codex to stop execution or…