subagent-driven-development

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

Updated Apr 25, 2026
One-click install
npx skills add https://github.com/tomasbasso/SistemaStockV2 --skill subagent-driven-development-tomasbasso
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/tomasbasso/SistemaStockV2/tree/main/.agents/skills/desarrollo-basado-en-subagentes
Command: npx skills add https://github.com/tomasbasso/SistemaStockV2 --skill subagent-driven-development-tomasbasso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill coordinates implementation planning within a single session by orchestrating independent subagents for each task and enforcing a two-stage review process, reducing feedback loops and accelerating delivery.

Core Features & Use Cases

  • Fresh subagent per task isolates context to maximize accuracy and reduce cross-task contamination.
  • Two-stage reviews: spec compliance first, then code quality, to ensure correct and maintainable outputs.
  • In-session execution supports rapid iteration for multi-task plans.

Quick Start

Dispatch an implementer subagent for each task from your plan and enable the two-stage reviews to guide completion.

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 multi-task development workflows with independent subagents?

Automating multi-task development workflows with independent subagents involves dispatching a fresh subagent per isolated task within a single session, applying spec-compliance and code-quality reviews to ensure accurate, maintainable outputs.

What is the best way to enforce spec compliance during automated code generation?

Enforcing spec compliance during automated code generation requires a two-stage review process that checks task outputs against the full plan context first, then applies a dedicated code-quality review before completion.

How does dispatching a fresh subagent per task reduce cross-task contamination?

Dispatching a fresh subagent per task isolates the execution context for each individual task, preventing cross-task contamination and maximizing accuracy by ensuring subagents operate without overlapping context.

Do I need a complete task plan before starting subagent-driven development?

Subagent-driven development requires a complete task plan with full text and context before execution, because the orchestration relies on largely independent tasks for rapid in-session iteration and two-stage reviews.

When should I avoid using subagent-driven development for task management?

You should avoid subagent-driven development when tasks are not largely independent or when rapid in-session iteration is unnecessary, as the fresh subagent orchestration and two-stage review process is optimized for fast, multi-task plans.