ralph-specum-refactor
The ralph-specum-refactor skill coordinates updates to Ralph Specum specification artifacts (requirements.md, design.md, tasks.md) after implementation reveals gaps or changes. Use this skill when a user explicitly requests Ralph Specum revision in Codex or asks to refactor specs based on implementation learnings. The skill delegates actual revision work to a refactor-specialist sub-agent, which preserves existing Ralph concepts like approval checkpoints and verification tasks while cascading updates downstream through the spec hierarchy.
git clone --depth 1 https://github.com/tzachbon/smart-ralph /tmp/ralph-specum-refactor && cp -r /tmp/ralph-specum-refactor/plugins/ralph-specum-codex/skills/ralph-specum-refactor ~/.claude/skills/ralph-specum-refactorSKILL.md
# Ralph Specum Refactor You are a **coordinator, not a refactor specialist** -- delegate spec revision to a `refactor-specialist` sub-agent. ## Contract - Resolve the active spec by explicit path, exact name, or `.current-spec` - Review files in order: `requirements.md`, `design.md`, `tasks.md` - Cascade downstream updates when upstream content changes - Reconcile `activePrototypes` and preserve unrelated refactor work ## Action 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 The sub-agent identifies what changed, what stayed accurate, and what is obsolete.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: - `requirements.md` - `design.md` - `tasks.md` 8. If requirements changed, revisit design and tasks. 9. If design changed, revisit tasks. 10. Record the rationale and cascade decisions in `.progress.md`. ## Response Handoff - After revising spec files, name the files that changed and summarize the updates briefly. - End with exactly one explicit choice prompt: - `approve current artifact` - `request changes` - `continue to implementation` - Treat `continue to implementation` as approval of the updated spec files.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs guidance on concise, scannable output formatting. Applies to all Ralph spec phase agents.
Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
This skill should be used when a Ralph phase must identify critical user decisions, run a layered grill, persist partial answers, obtain explicit approval, or resume an interrupted phase interview before delegating artifact work.
Internal Ralph Specum contract for Codex phase interviews, skill manifests, approval, and delegation gates. Phase coordinators load this skill directly; users do not invoke it as a workflow phase.
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.