subagent-driven-development

Dispatch isolated subagents for independent tasks with two-stage validation reviews.

4|1|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/shichengwuyu/PaiJiPlus --skill subagent-driven-development-shichengwuyu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/shichengwuyu/PaiJiPlus/tree/main/.trae/skills/subagent-driven-development
Command: npx skills add https://github.com/shichengwuyu/PaiJiPlus --skill subagent-driven-development-shichengwuyu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates plan execution by dispatching fresh subagents to handle independent tasks within the current session, ensuring isolated context and structured validation.

Core Features & Use Cases

  • Fresh subagent per task with isolated context to prevent cross-task leakage.
  • Two-stage review workflow after each task: spec compliance review first, then code quality review.
  • Clear per-task workflow (read plan, extract tasks, dispatch implementer, then review) that scales to multi-task plans.
  • Self-review and escalation prompts to handle BLOCKED or NEEDS_CONTEXT scenarios.
  • Templates for implementer, spec reviewer, and code-quality reviewer to enforce consistent processes.

Quick Start

Start by dispatching the first task using the plan, then let a fresh subagent execute it with two-stage reviews.

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate subagent task execution with isolated context for multi-task plans?

Subagent task orchestration dispatches fresh isolated subagents to handle independent tasks within a session, preventing cross-task context leakage. It uses dedicated templates for implementer, spec reviewer, and code-quality reviewer to enforce structured validation.

What is a two-stage review workflow for code quality and spec compliance?

A two-stage review workflow validates completed tasks sequentially: spec compliance review first, then code quality review. This structured validation flow uses dedicated templates to ensure both requirements adherence and code standards are met.

How do I handle blocked tasks or missing context during subagent-driven development?

Subagent-driven development handles blocked tasks or missing context through self-review and escalation prompts. These mechanisms allow isolated subagents to flag issues and request additional information during task execution.

Can I use subagent-driven development for plans with multiple discrete tasks?

Subagent-driven development suits plans with multiple discrete tasks that benefit from context isolation and structured validation. It scales by extracting tasks from the plan, dispatching implementer subagents, and conducting per-task two-stage reviews.

When should I not use isolated subagents for plan execution?

Isolated subagents for plan execution are not suitable for tasks lacking independence or requiring shared cross-task context. The workflow relies on discrete task boundaries to maintain context isolation and structured validation.