skills.rest
NagyVikt
NagyViktCOMMUNITY
Explore all skills by this author →
Website𝕏@NagyViktordpGitHub

subagent-driven-development

Dispatch specialized subagents to implement and verify multi-task development plans.

2|Updated Mar 29, 2026
Search Tags:#automation#workflow#tdd#development#subagent#code-review
One-click install
npx skills add https://github.com/NagyVikt/codex-plugins --skill subagent-driven-development-nagyvikt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/NagyVikt/codex-plugins/tree/main/plugins/superpowers/skills/subagent-driven-development
Command: npx skills add https://github.com/NagyVikt/codex-plugins --skill subagent-driven-development-nagyvikt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of managing complex, multi-task development projects by automating the dispatch, execution, and rigorous review of individual implementation tasks within a single session.

Core Features & Use Cases

  • Autonomous Task Execution: Dispatches specialized subagents to handle implementation, spec compliance, and code quality reviews.
  • Two-Stage Quality Gates: Ensures every task passes both a spec compliance check and a code quality review before being marked as complete.
  • Use Case: When you have a large feature plan, use this skill to break it down into independent tasks, where each task is implemented, tested, and reviewed by AI subagents without requiring constant manual intervention.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at docs/plans/feature-plan.md by following the two-stage review process.

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 development plan execution with AI subagents?▼

Automated development plan execution is handled by dispatching specialized subagents to implement individual tasks and verify spec compliance without requiring constant manual intervention. This orchestrates multi-task implementation plans within a single session.

Can I enforce test-driven development and code review automatically in my workflow?▼

Test-driven development and automated code review are enforced through a two-stage quality gate process. Every task must pass both a spec compliance check and a code quality review by subagents before being marked as complete.

What is the best way to manage isolated implementation tasks for a large feature plan?▼

Managing isolated implementation tasks is best achieved by breaking down a large feature plan into independent pieces. Specialized subagents then handle the implementation, testing, and review of each isolated task autonomously.

How does multi-stage verification work for AI-generated code?▼

Multi-stage verification for AI-generated code works by applying a two-stage review process where subagents independently check for spec compliance and code quality. This rigorous verification ensures high-quality, TDD-compliant code generation before task completion.

Do I need to provide a specific file format to start automated task dispatch?▼

You need to provide a markdown implementation plan file, such as one located at docs/plans/feature-plan.md. The subagents use this file to break down the work and follow the two-stage review process for execution.

Related Skills

Explore More Software Engineering Skills→
kimprobablykimprobably

subagent-driven-development

Execute implementation plans by dispatching fresh subagents per task with two-stage reviews.

Community
Advanced
dmedina-devdmedina-dev
1

subagent-driven-development

Execute implementation plans by dispatching fresh subagents for each task.

Community
Advanced
jacexhjacexh

subagent-driven-development

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

Community
Advanced
SignmanalSignmanal
1

subagent-driven-development

Delegate implementation tasks to isolated subagents with automated two-stage reviews.

Community
Advanced