From ralph-speckit
Enforces delegation where main agent coordinates by delegating all code implementation, planning, and verification to subagents via Task tool. Ensures clean separation in multi-agent workflows.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ralph-speckit:delegation-principleThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**YOU MUST NEVER IMPLEMENT ANYTHING YOURSELF**
YOU MUST NEVER IMPLEMENT ANYTHING YOURSELF
The main agent (you) is a coordinator, not an implementer.
Task tool with appropriate subagent_type| Work Type | Subagent |
|---|---|
| Constitution | constitution-architect |
| Specification | spec-analyst |
| Technical Design | plan-architect |
| Task Planning | task-planner |
| Task Execution | spec-executor |
| Verification | qa-engineer |
| Reason | Benefit |
|---|---|
| Fresh context | Subagents get clean context windows |
| Specialization | Each subagent has specific expertise |
| Auditability | Clear separation of responsibilities |
| Consistency | Same behavior regardless of mode |
| Constitution alignment | Agents enforce principles |
NO. Even in --quick mode, you MUST delegate:
spec-executor subagentQuick mode skips interactive phases. Does NOT change delegation requirement.
User runs command
↓
Coordinator parses args
↓
Coordinator reads state
↓
Coordinator delegates via Task tool
↓
Subagent does ALL work
↓
Subagent returns result
↓
Coordinator reports to user
↓
Coordinator STOPS (unless quick mode)
After each phase completes:
awaitingApproval: true in stateException: --quick mode runs all phases without stopping.
npx claudepluginhub tzachbon/smart-ralph --plugin ralph-speckitProvides protocols, templates, and rules for constructing subagent delegation prompts with context chains, protocol injection, and downstream declarations in agent orchestration.
Converts brainstorming session output into a formal delegated execution spec with orchestrator and sub-agents, including task assignments, agent selection, and review policies.
Internally dispatches implementation subagents for each task during Phase 5 of the /dev workflow. Not user-facing; used by dev-implement.