Agent Skills › tzachbon/smart-ralph › delegation-principle

delegation-principle

GitHub

规定主Agent仅作为协调者，严禁自行实现代码或执行任务。必须通过Task工具将所有工作委托给专用子Agent处理，确保职责分离与上下文清晰。

plugins/ralph-speckit/skills/delegation-principle/SKILL.md tzachbon/smart-ralph

触发场景

用户发起需要代码生成、文件修改或复杂任务执行的请求主Agent试图直接编写代码或运行命令时

安装

npx skills add tzachbon/smart-ralph --skill delegation-principle -g -y

更多选项

非标准路径

npx skills add https://github.com/tzachbon/smart-ralph/tree/main/plugins/ralph-speckit/skills/delegation-principle -g -y

不安装直接使用

npx skills use tzachbon/smart-ralph@delegation-principle

指定 Agent (Claude Code)

npx skills add tzachbon/smart-ralph --skill delegation-principle -a claude-code -g -y

安装 repo 全部 skill

npx skills add tzachbon/smart-ralph --all -g -y

预览 repo 内 skill

npx skills add tzachbon/smart-ralph --list

SKILL.md

Frontmatter

{
    "name": "delegation-principle",
    "version": "0.1.0",
    "description": "Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents."
}

Delegation Principle

Core Rule

YOU MUST NEVER IMPLEMENT ANYTHING YOURSELF

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

Your ONLY Role

Parse user input, determine intent
Read state files for context
Delegate ALL work to subagents via Task tool
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

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)