skills.rest
leonardoteodoroo
leonardoteodorooCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

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

Updated Feb 3, 2026
Search Tags:#workflow#subagents#code-review#software-engineering#plan-execution#spec-review
One-click install
npx skills add https://github.com/leonardoteodoroo/amino-advanced --skill subagent-driven-development-leonardoteodoroo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/leonardoteodoroo/amino-advanced/tree/main/.agent/skills/subagent-driven-development
Command: npx skills add https://github.com/leonardoteodoroo/amino-advanced --skill subagent-driven-development-leonardoteodoroo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables teams to orchestrate independent subagents to execute complex plans with staged reviews, improving iteration speed and quality.

Core Features & Use Cases

  • Fresh per-task subagents to prevent context pollution and enable parallel, isolated work
  • Two-stage review workflow: spec compliance first, then code quality
  • Flexible execution modes (same-session flow or parallel session) to scale throughput and ensure quality

Quick Start

Load the current plan and let the system dispatch per-task subagents with staged reviews.

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 software engineering plans with automated code review?▼

Automated code review for plan execution works by dispatching fresh subagents to implement tasks, followed by dedicated spec and code quality reviewer subagents validating the output in a two-stage loop.

What is a subagent-driven development workflow?▼

Subagent-driven development is a workflow that dispatches isolated subagents for each task to prevent context pollution, enabling parallel work and staged reviews for fast iteration.

How do subagents prevent context pollution during code generation?▼

Subagents prevent context pollution by spinning up fresh, isolated instances for each task, ensuring prior implementation and review history does not degrade subsequent code generation quality.

Can I run parallel sessions for independent software engineering tasks?▼

Yes, you can run parallel sessions for independent software engineering tasks. The system supports flexible execution modes to scale throughput and maintain quality across independent tasks.

When should I use a two-stage spec and code quality review process?▼

Use a two-stage spec and code quality review process when orchestrating complex plans with mostly independent tasks. It is best suited for single sessions requiring fast iteration and staged quality enforcement.

Do I need a predefined plan to use subagent orchestration?▼

Yes, you need a predefined plan to use subagent orchestration. The system dispatches per-task implementer and reviewer subagents based on the loaded plan to execute the staged review workflow.

Related Skills

Explore More Software Engineering Skills→
galangryandanagalangryandana
20

subagent-driven-development

Dispatch fresh subagents to execute independent implementation tasks with two-stage reviews.

Community
Advanced
lovecrushfamilylovecrushfamily
1

vc-autoresearch

Automate iterative gap detection and fixing in software specifications, tests, and UX.

Community
Advanced
kjayleekjaylee

subagent-dev

Dispatch implementation tasks to subagents with two-stage spec and code review.

Community
Advanced
SighthesiaSighthesia
4

subagent-driven-development

Dispatch a fresh subagent per task and review code between tasks.

Community
Advanced