ralph-specum

Cancel active execution loop, cleanup state, and remove spec

Generate technical design from requirements

Submit feedback or report an issue for Ralph Specum plugin.

Show help for Ralph Specum plugin commands and workflow.

You are starting the task execution loop.

You are running the codebase indexing command. This scans the repository to generate component specs in `specs/.index/`.

Create new spec and start research phase

Update specification files after execution. You are a **coordinator, not a writer** -- delegate actual updates to the `refactor-specialist` subagent.

Generate requirements from goal and research

Run or re-run research phase for current spec

Smart entry point for ralph-specum. Detects whether to create a new spec or resume an existing one.

Show all specs and their current status

Switch active spec

Generate implementation tasks from design

This agent should be used to "create technical design", "define architecture", "design components", "create design.md", "analyze trade-offs". Expert systems architect that designs scalable, maintainable systems with clear component boundaries.

This agent should be used to "generate requirements", "write user stories", "define acceptance criteria", "create requirements.md", "gather product requirements". Expert product manager that translates user goals into structured requirements.

This agent should be used to "run verification task", "check quality gate", "verify acceptance criteria", "run [VERIFY] task", "execute quality checkpoint". QA engineer that runs verification commands and outputs VERIFICATION_PASS or VERIFICATION_FAIL.

This agent should be used to "update spec files", "refactor requirements", "revise design", "modify tasks after execution", "incrementally update specifications". Expert at methodically reviewing and updating spec files section-by-section after execution.

This agent should be used to "research a feature", "analyze feasibility", "explore codebase", "find existing patterns", "gather context before requirements". Expert analyzer that verifies through web search, documentation, and codebase exploration before providing findings.

This agent should be used to "execute a task", "implement task from tasks.md", "run spec task", "complete verification task". Autonomous executor that implements one task, verifies completion, commits changes, and signals TASK_COMPLETE.

This agent should be used to "review artifact", "validate spec output", "check quality", "review research output", "review requirements", "review design", "review tasks", "review execution". Read-only reviewer that validates artifacts against type-specific rubrics and outputs REVIEW_PASS or REVIEW_FAIL.

This agent should be used to "create tasks", "break down design into tasks", "generate tasks.md", "plan implementation steps", "define quality checkpoints". Expert task planner that creates POC-first task breakdowns with verification steps.

This skill should be used when the user asks about "output formatting", "concise responses", "Matt Pocock planning style", "scannable output", "action steps format", or needs guidance on communication and output formatting rules for Ralph agents.

This skill should be used when the user asks about "coordinator role", "delegate to subagent", "use Task tool", "never implement yourself", "subagent delegation", or needs guidance on proper delegation patterns for Ralph workflows.

Adaptive brainstorming-style dialogue for all spec phases (Understand, Propose Approaches, Confirm & Store)

This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", or needs guidance on verifying fixes by reproducing failures before and after implementation.

This skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "execution modes", "ralph loop integration", or needs guidance on common Ralph plugin arguments and state management patterns.

This skill should be used when the user asks to "build a feature", "create a spec", "start spec-driven development", "run research phase", "generate requirements", "create design", "plan tasks", "implement spec", "check spec status", or needs guidance on the spec-driven development workflow.

3 hooks across 3 events