subagent-task-execution

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Subagent Task Execution

Subagent 任务执行

Overview

概述

This skill is used to execute a set of tasks (typically from a task breakdown or plan). It focuses on high-quality execution by dispatching specialized subagents for each task, ensuring each task is performed correctly and verified before moving to the next.

本skill用于执行一组任务（通常来自任务分解或计划）。它专注于高质量执行，为每个任务调度专业的subagent，确保在进入下一个任务前，每个任务都被正确执行并通过验证。

Core Principle

核心原则

One Task, One Subagent, Multi-Stage Review. By isolating each task and applying a structured review process, we ensure high quality and prevent context pollution.

一任务、一Subagent、多阶段评审。 通过隔离每个任务并应用结构化评审流程，我们确保高质量输出并避免上下文污染。

The Process

执行流程

Preparation:
- Read the entire plan or task breakdown.
- Extract all tasks with their full context.
- Create a structured todo list using the
```
TodoWrite
```
  tool.
Per-Task Execution Loop:
- Skill Discovery: Before starting a task, identify which specialized skill(s) are needed for its execution (e.g.,
```
coding
```
  ,
```
brainstorming
```
  , or any project-specific skills).
- Dispatch Implementer: Dispatch a subagent to perform the task. Provide the subagent with the full task description, any identified skills, and the necessary context.
- Interactive Clarification: If the subagent has questions, answer them clearly before they proceed with implementation.
- Task Implementation: The subagent performs the task, following the identified best practices and skills.
- Verification & Review:
  - Spec Compliance Review: A separate subagent verifies that the result exactly matches the task requirements (no more, no less).
  - Quality Review: A final review stage to ensure the output meets the highest standards of the domain (e.g., code quality, documentation clarity, etc.).
- Completion: Mark the task as completed in the todo list.
Finalization:
- Once all tasks are complete, perform a final holistic review of the entire body of work to ensure consistency and overall quality.

准备阶段：
- 通读整个计划或任务分解文档。
- 提取所有任务及其完整上下文。
- 使用
```
TodoWrite
```
  工具创建结构化待办事项列表。
单任务执行循环：
- 技能发现： 在开始任务前，确定执行该任务所需的专业skill（例如
```
coding
```
  、
```
brainstorming
```
  或任何项目特定技能）。
- 调度执行者： 调度一个subagent来执行任务。向subagent提供完整的任务描述、已识别的技能及必要上下文。
- 交互式澄清： 如果subagent有疑问，在其开始实施前清晰解答。
- 任务实施： subagent按照已确定的最佳实践和技能执行任务。
- 验证与评审：
  - 合规性评审： 由独立的subagent验证结果是否完全符合任务要求（不多不少）。
  - 质量评审： 最终评审阶段，确保输出符合该领域的最高标准（例如代码质量、文档清晰度等）。
- 完成标记： 在待办事项列表中标记该任务为已完成。
收尾阶段：
- 所有任务完成后，对整个工作成果进行最终整体评审，确保一致性和整体质量。

Key Principles

关键原则

Discovery First: Always look for and apply the most relevant skills for the specific task at hand.
Isolation: Each task should be treated as a distinct unit of work.
Review Loops: Never move to the next task if the current one has open issues from either the spec or quality reviews.
Subagent Specialization: Use subagents as specialized workers, providing them with all the context they need upfront.

先发现技能： 始终为特定任务寻找并应用最相关的技能。
任务隔离： 每个任务应被视为独立的工作单元。
评审闭环： 如果当前任务在合规性或质量评审中存在未解决问题，绝不推进到下一个任务。
Subagent专业化： 将subagent视为专业工作者，提前为其提供所需的全部上下文。

Red Flags

注意事项（红牌警示）

Skipping the skill discovery phase.
Combining multiple tasks into a single subagent invocation.
Proceeding with a task while reviews are still pending or failing.
Ignoring subagent questions or providing vague answers.
Failing to update the todo list as progress is made.

跳过技能发现阶段。
将多个任务合并为单次subagent调用。
在评审未完成或不通过的情况下推进任务。
忽略subagent的问题或提供模糊的回答。
未随进度更新待办事项列表。