delegation-principle

$npx mdskill add tzachbon/smart-ralph/delegation-principle

Coordinates work by delegating tasks to specialized subagents

  • Handles user input and context for task delegation.
  • Uses Task tool to delegate all work to appropriate subagents.
  • Subagents perform specific tasks like constitution, specification, design, execution, verification.
  • Delivers results directly to the user without direct implementation.

SKILL.md

.github/skills/delegation-principleView on GitHub ↗
---
name: delegation-principle
description: Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.
version: 0.1.0
---

# Delegation Principle

## Core Rule

**YOU MUST NEVER IMPLEMENT ANYTHING YOURSELF**

The main agent (you) is a **coordinator**, not an implementer.

## Your ONLY Role

1. Parse user input, determine intent
2. Read state files for context
3. **Delegate ALL work to subagents via Task tool**
4. Report results to user

## NEVER Do

- Write code, create files, modify source directly
- Run implementation commands (npm, git commit, file edits)
- Perform research, analysis, or design yourself
- Execute task steps from tasks.md yourself
- "Help out" by doing small parts directly
- Generate spec artifacts (spec.md, plan.md, tasks.md) yourself

## ALWAYS Do

- Use `Task` tool with appropriate `subagent_type`
- Pass complete context to subagent
- Wait for subagent completion before proceeding
- Let subagent handle ALL implementation details

## SpecKit Subagent Types

| Work Type | Subagent |
|-----------|----------|
| Constitution | `constitution-architect` |
| Specification | `spec-analyst` |
| Technical Design | `plan-architect` |
| Task Planning | `task-planner` |
| Task Execution | `spec-executor` |
| Verification | `qa-engineer` |

## Why This Matters

| 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 |

## Quick Mode Exception?

**NO.** Even in `--quick` mode, you MUST delegate:
- Artifact generation → appropriate specialist subagent
- Task execution → `spec-executor` subagent

Quick mode skips interactive phases. Does NOT change delegation requirement.

## Coordinator Pattern

```text
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)
```

## Phase Transitions

After each phase completes:

1. Subagent sets `awaitingApproval: true` in state
2. Coordinator outputs status with next command
3. Coordinator STOPS immediately
4. User must run next command explicitly

Exception: `--quick` mode runs all phases without stopping.

More from tzachbon/smart-ralph

SkillDescription
Command DevelopmentThis 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.
communication-styleOutput rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.
Hook DevelopmentThis 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 ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
interview-frameworkThis skill should be used when running an interactive interview before a spec phase, gathering requirements through dialogue, asking the user clarifying questions before delegating to a subagent, or when any Ralph phase command (research, requirements, design, tasks) needs adaptive brainstorming dialogue. Covers the 3-phase algorithm (Understand, Propose Approaches, Confirm and Store).
MCP IntegrationThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${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.
Plugin SettingsThis 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.
Plugin StructureThis skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
ralph-specumUse only when the user explicitly invokes `$ralph-specum`, requests Ralph Specum in Codex, asks Ralph Specum to handle a named phase, or explicitly requests autonomous or quick mode or continuation without pauses.
ralph-specum-cancelThis skill should be used only when the user explicitly asks to use `$ralph-specum-cancel`, or explicitly asks Ralph Specum in Codex to stop execution or remove a spec.
ralph-specum-designThis skill should be used only when the user explicitly asks to use `$ralph-specum-design`, or explicitly asks Ralph Specum in Codex to run the design phase.