skills.rest
AvaTar-ArTs
AvaTar-ArTsCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch fresh subagents per task and apply two-stage reviews.

Updated May 11, 2026
Search Tags:#automation#workflow#development#subagent#ai-assistant#plan-execution
One-click install
npx skills add https://github.com/AvaTar-ArTs/my-supremepowers --skill subagent-driven-development-avatar-arts
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/AvaTar-ArTs/my-supremepowers/tree/main/qwen_skills/superpowers-subagent-driven-development
Command: npx skills add https://github.com/AvaTar-ArTs/my-supremepowers --skill subagent-driven-development-avatar-arts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Disjointed plan execution often stalls progress. This skill solves that by dispatching fresh subagents per task and enforcing a two-stage review workflow to maintain quality and momentum.

Core Features & Use Cases

  • Fresh subagent per task to keep context isolated and avoid cross-task contamination.
  • Two-stage reviews (spec compliance, then code quality) to catch issues early.
  • Structured plan execution for complex, multi-task implementations within a single session.
  • Predefined prompt templates for implementer, spec reviewer, and code-quality reviewer to standardize workflows.
  • Useful in scenarios where tasks are mostly independent but must be coordinated to a single plan.

Quick Start

Provide a plan, then dispatch a subagent for each task and run the two-stage review loop for every 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 complex plan execution with fresh subagents per task?▼

Automated plan execution dispatches a fresh subagent per task to isolate context, then applies a two-stage review loop to maintain code quality and momentum across multiple independent tasks within a single session.

What is the best way to prevent cross-task context contamination in AI-assisted development?▼

Preventing cross-task context contamination requires dispatching a fresh subagent for each task, ensuring isolated execution contexts that keep independent implementation steps from interfering with one another.

How do I set up two-stage reviews for multi-task implementation workflows?▼

Setting up two-stage reviews requires predefined prompt templates for a spec reviewer and a code-quality reviewer, which are automatically applied to enforce structured reviews after each task implementation.

Can I use subagent-driven development for coordinated but independent implementation tasks?▼

Subagent-driven development suits scenarios where tasks are mostly independent but must be coordinated to a single plan, standardizing the workflow through structured execution and automated self-review loops.

Why does disjointed plan execution stall progress in multi-task development?▼

Disjointed plan execution stalls progress due to overlapping contexts and unstandardized reviews; enforcing per-task isolation and two-stage automated reviews resolves this by maintaining quality and momentum.

Related Skills

Explore More Software Engineering Skills→
seankao31seankao31

subagent-driven-development

Dispatch isolated subagents to implement plan tasks with per-task reviews.

Community
Advanced
venhdevvenhdev

subagent-driven-development

Dispatch isolated subagents for each task with automated review gates.

Community
Advanced
tangzheng202202tangzheng202202
1

subagent-driven-development

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

Community
Advanced
tusosostusosos

subagent-driven-development

Dispatch fresh subagents per task to isolate context and run two-stage reviews.

Community
Advanced