skills.rest
hubeiqiao
hubeiqiaoCOMMUNITY
Explore all skills by this author →
Website𝕏@hubeiqiaoGitHub

subagent-driven-development

Dispatch independent subagents for discrete tasks with code review gates.

Updated Mar 4, 2026
Search Tags:#code review#task management#parallel execution#iterative development#agile development#subagent
One-click install
npx skills add https://github.com/hubeiqiao/skills --skill subagent-driven-development-hubeiqiao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/hubeiqiao/skills/tree/main/subagent-driven-development
Command: npx skills add https://github.com/hubeiqiao/skills --skill subagent-driven-development-hubeiqiao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines complex development tasks by breaking them down into independent sub-tasks, each handled by a fresh AI agent, ensuring quality through iterative reviews and enabling faster development cycles.

Core Features & Use Cases

  • Task Decomposition: Divides large plans into manageable, independent tasks.
  • Subagent Dispatch: Assigns each task to a new, unpolluted agent instance for focused execution.
  • Iterative Review: Incorporates code review checkpoints between tasks to catch errors early.
  • Sequential & Parallel Execution: Supports both ordered task execution and concurrent handling of unrelated issues.
  • Use Case: Developing a new feature with multiple components. The skill can assign one subagent to build the backend API, another to develop the frontend UI, and a third to write integration tests, with reviews after each stage.

Quick Start

Use the subagent-driven-development skill to execute the plan located at /path/to/your/plan.md.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I break down a complex software feature into independent development tasks?▼

Subagent-driven development decomposes large plans into discrete, manageable sub-tasks. Each task is assigned to a fresh AI agent instance for focused, unpolluted execution to streamline complex feature implementation.

Can I run parallel execution for unrelated coding tasks instead of processing them sequentially?▼

Yes, subagent-driven development supports both sequential and parallel execution workflows. This allows concurrent handling of unrelated software issues while maintaining ordered execution for dependent tasks.

How does iterative development with subagents handle code review and quality assurance?▼

Iterative development incorporates code review checkpoints between subagent tasks to catch errors early. Automated task completion tracking and staged verification ensure robust error handling throughout the process.

What is the best way to automate task management for multi-component agile development?▼

Subagent-driven development automates task management by dispatching independent subagents for each component within a larger plan. It tracks completion automatically and enforces quality gates through iterative reviews.

Do I need a predefined plan file to start iterative software development with subagents?▼

Yes, you need a plan file to execute iterative software development with subagents. The skill reads your plan, breaks it into independent sub-tasks, and dispatches fresh agents to handle each component sequentially or in parallel.

When should I avoid using subagent-driven development for task decomposition?▼

Avoid subagent-driven development for simple, single-step coding tasks that do not require task decomposition or iterative review. It is designed for complex, multi-component plans that benefit from staged implementation and parallel execution.

Related Skills

Explore More Software Engineering Skills→
Bbeierle12Bbeierle12
8

subagent-driven-development

Dispatch independent subagents for discrete implementation tasks with review checkpoints.

Community
Basic
CyapstayeCyapstaye
9

test-driven-development

Enforce the Red-Green-Refactor cycle with failing tests before implementation.

Community
Advanced
kynetic-aikynetic-ai
1

pr-review

Validate kspec task PRs against acceptance criteria and spec alignment before merging.

Official
Advanced
agusmdevagusmdev
3

open-prose

Orchestrate multi-agent AI workflows with a declarative VM.

Community
Advanced