subagent-driven-development

Delegate independent implementation tasks to fresh subagents and review each result.

1|Updated Apr 14, 2026
One-click install
npx skills add https://github.com/51hhh/BU03 --skill subagent-driven-development-51hhh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/51hhh/BU03/tree/main/.github/skills/subagent-driven-development
Command: npx skills add https://github.com/51hhh/BU03 --skill subagent-driven-development-51hhh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you execute implementation plans without losing focus by splitting work into independent tasks and handing each one to a fresh subagent.

Core Features & Use Cases

  • Task Delegation: Assign each implementation task to a separate subagent with only the context it needs.
  • Two-Stage Review: Verify every task first for spec compliance and then for code quality before moving on.
  • Iterative Recovery: Handle questions, blockers, and review feedback without polluting the main session.
  • Use Case: A developer can use this Skill to carry a multi-step feature plan through implementation, review, fixes, and completion in one session.

Quick Start

Use the subagent-driven-development skill to execute the current implementation plan by delegating each task to a fresh subagent and reviewing the result for spec compliance before code quality.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I execute implementation plans without losing context in a long development session?

You can execute implementation plans by delegating independent tasks to fresh subagents, ensuring each task only receives the specific context it needs without inheriting prior session pollution.

What is the two-stage review process for subagent task delegation?

The two-stage review process verifies every delegated task result first for spec compliance and then for code quality, ensuring both functional requirements and standards are met before proceeding.

How do I handle blockers and review feedback when delegating tasks to subagents?

You handle blockers and review feedback through iterative recovery, resolving questions and issues within the delegated subagent context to prevent polluting the main development session.

Can I use subagent-driven development for multi-step feature implementation in a single session?

Yes, you can use subagent-driven development for same-session workflows where multi-step feature plans are split into independent tasks, implemented, validated, and sequentially reviewed.

Why does task delegation require fresh subagents for each implementation step?

Fresh subagents are required because they execute tasks without inheriting prior context, allowing focused implementation and reliable execution through task-level context packaging.

What are the limitations of using subagents for iterative code review and task delegation?

This approach is limited to same-session development workflows where tasks can be cleanly split and validated independently, requiring explicit blocker handling and task-level context packaging for reliable execution.