skills.rest
yashs33244
yashs33244COMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and code review.

1|Updated May 5, 2026
Search Tags:#code review#subagents#plan execution#test-driven development#software delivery#spec compliance#task orchestration
One-click install
npx skills add https://github.com/yashs33244/my-mac-claude --skill subagent-driven-development-yashs33244
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/yashs33244/my-mac-claude/tree/main/skills/superpowers/subagent-driven-development
Command: npx skills add https://github.com/yashs33244/my-mac-claude --skill subagent-driven-development-yashs33244

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Subagent-driven development eliminates slow, error-prone task execution by running each implementation task in isolation and enforcing two-stage review (spec compliance first, then code quality) after every task.

Core Features & Use Cases

  • Fresh subagent per task to prevent context pollution and keep work focused.
  • Two-stage review loop (spec compliance, then code quality) to catch both missing requirements and implementation problems early.
  • Continuous plan execution to avoid unnecessary check-ins while still escalating correctly when blocked or needing context.

Quick Start

Use this skill when you have an implementation plan with multiple mostly independent tasks and want to execute them sequentially without pausing for check-ins, using isolated implementer and reviewer subagents per 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 automate plan execution for multiple independent coding tasks?▼

Automate plan execution by dispatching a fresh subagent per task to implement code in isolation, ensuring focused progress without context pollution across your entire task list.

What is two-stage code review for subagent task orchestration?▼

Two-stage review enforces spec compliance first, then code quality, after every implementation task. Implementer subagents are iteratively re-dispatched with fixes until both reviewers approve the work.

How do I run uninterrupted software delivery without pausing for check-ins?▼

Run continuous plan execution by isolating context per subagent and handling implementer statuses explicitly, escalating only when blocked or requiring additional context to proceed.

Can I use subagent-driven development for dependent tasks in the same session?▼

This approach applies when tasks are mostly independent. Relying on isolated subagent contexts works best for uninterrupted sequential progress rather than tightly coupled dependent tasks.

How does test-driven development integrate with subagent task execution?▼

Test-driven development integrates by using the two-stage review loop to catch missing requirements and implementation problems early, re-dispatching subagents until spec compliance and code quality pass.

Related Skills

Explore More Software Engineering Skills→
Donaldshen27Donaldshen27

subagent-driven-development

Orchestrate subagent-driven development by dispatching per-task agents with code-review checkpoints.

Community
Advanced
marcusglee11marcusglee11

close-build

Merge a completed development branch into main with cleanup and gate enforcement.

Community
Intermediate
HankLiu447HankLiu447
3

code-review

Automate two-stage code reviews for specification compliance and code quality.

Community
Intermediate
rm2thaddeusrm2thaddeus
4

subagent-driven-development

Orchestrate AI subagents to implement plans with two-stage reviews.

Community
Advanced