skills.rest
m16khb
m16khbCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch fresh subagents per task with code review and test gates.

Updated Dec 2, 2025
Search Tags:#planning#subagents#iteration#review#execution
One-click install
npx skills add https://github.com/m16khb/claude-integration --skill subagent-driven-development-m16khb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/m16khb/claude-integration/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/m16khb/claude-integration --skill subagent-driven-development-m16khb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill orchestrates execution by dispatching fresh subagents for each task, with per-task code review to ensure rapid iteration and high quality.

Core Features & Use Cases

  • Sequential Execution: Dispatch tasks one by one with per-task review.
  • Parallel Execution: Dispatch independent tasks concurrently for speed.
  • Code Review Gate: Enforce quality between tasks.
  • Usage Scenario: Implement Plan N by distributing sub-tasks to fresh agents and reviewing results after each.

Quick Start

Dispatch two tasks: "Implement feature A" and "Add tests for A"; review results after each task.

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 multiple implementation tasks in parallel with code review gates?▼

Dispatch independent tasks concurrently to fresh subagents, then enforce per-task code review before progressing. This pattern accelerates iteration while maintaining quality checks between execution stages.

Can I use subagent dispatch for tightly coupled implementation tasks?▼

Yes. Subagent-driven development handles both sequential execution of dependent tasks and parallel execution of independent ones. Each task receives a fresh subagent, with review gates and explicit completion marking between stages.

What's the best way to structure a multi-task implementation plan for fast iteration?▼

Break the plan into 3+ discrete tasks, dispatch each to a fresh subagent for isolated execution, run post-task code review and test reporting, then explicitly gate fixes and final validation. This separation enables rapid turnaround without shared state conflicts.

When should I use sequential execution versus parallel subagent dispatch?▼

Use sequential execution when tasks are tightly coupled and require review between stages. Use parallel dispatch for independent domain tasks to accelerate overall completion while maintaining per-task review quality gates.

Do I need to manage state across subagent executions in this workflow?▼

No. Each subagent operates independently on its assigned task. The workflow design eliminates shared state by dispatching fresh agents per task, reducing coordination overhead and enabling concurrent execution.

Related Skills

Explore More Software Engineering Skills→
Owl-ListenerOwl-Listener
234

writing-design-plans

Breaks approved design directions into discrete tasks with acceptance criteria and accessibility considerations.

Community
Advanced
luongldptitluongldptit

laravel-verification

Run sequential Laravel environment, code quality, test, security, and deployment checks.

Community
Advanced
lespacemanlespaceman
4

subagent-driven-development

Dispatch isolated subagents per task with two-stage spec and code-quality reviews.

Community
Advanced
zinohomezinohome

dispatching-parallel-agents

Coordinate parallel delegation of independent tasks across specialized agents.

Community
Intermediate