skills.rest
minhhh
minhhhCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

subagent-driven-development

Dispatches subagents for each task with two-stage reviews and a final code merge.

Updated Apr 16, 2014
Search Tags:#subagents#code-quality#development-workflow#spec-compliance#task-dispatch#review-pipeline
One-click install
npx skills add https://github.com/minhhh/dotfiles --skill subagent-driven-development-minhhh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/minhhh/dotfiles/tree/main/ai/.ai/gemini-superpowers/skills/subagent-driven-development
Command: npx skills add https://github.com/minhhh/dotfiles --skill subagent-driven-development-minhhh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinated task execution can be slow and error-prone when relying on a single agent; this skill accelerates plan execution by dispatching fresh subagents per task and enforcing two-stage reviews to improve quality and iteration speed.

Core Features & Use Cases

  • Fresh subagent per task to isolate context and avoid context pollution.
  • Two-stage review after each task: spec compliance review, followed by code quality review.
  • End-to-end task orchestration within a single session for iterative development and rapid feedback.

Quick Start

Dispatch the per-task subagents as you execute your plan.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I isolate context for independent tasks in a multi-step development workflow?▼

Multi-step development workflows can isolate context by dispatching a fresh subagent for each independent task. This prevents context pollution and enforces a structured pipeline with two-stage reviews to maintain code quality.

What's the best way to enforce spec compliance and code quality during task execution?▼

Spec compliance and code quality are enforced via a two-stage review pipeline after each task. This applies spec-reviewer prompts and code-quality-reviewer prompts to evaluate outputs before proceeding to a final code merge step.

Can I orchestrate complex, multi-step plans within a single session using fresh subagents?▼

Complex, multi-step plans can be orchestrated within a single session by dispatching fresh subagents for each task. This accelerates execution for mostly independent tasks by applying isolated context and rapid feedback loops.

How does a two-stage review pipeline work for task dispatch?▼

The two-stage review pipeline for task dispatch applies a spec compliance review followed by a code quality review after each task. It uses implementer, spec-reviewer, and code-quality-reviewer prompts before a final code merge step.

When should I not use fresh subagents for task orchestration?▼

Fresh subagents for task orchestration should not be used for tasks with heavy interdependencies. This approach is designed for mostly independent tasks where isolated context is needed to avoid context pollution and improve review pipelines.

Related Skills

Explore More Software Engineering Skills→
Marwan78888Marwan78888
16

subagent-driven-development

Dispatch plan tasks to fresh subagents with two-stage reviews.

Community
Advanced
cookeyholdercookeyholder

executing-plans

Executes a written plan with review checkpoints and stepwise verification.

Community
Advanced
zizzfizzixzizzfizzix

code-review

Automate code review for architectural, security, and quality compliance.

Community
Advanced
scooter-lacroixscooter-lacroix
8

implement_plan

Implement technical plans from file paths with risk checks and verification.

Community
Advanced