subagent-driven-development

Execute implementation plans with independent subagents for two-stage reviews.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/christhz666/centro-diagnostico-v11 --skill subagent-driven-development-christhz666
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/christhz666/centro-diagnostico-v11/tree/main/.skills/subagent-driven-development
Command: npx skills add https://github.com/christhz666/centro-diagnostico-v11 --skill subagent-driven-development-christhz666

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires subagent-prompting, and includes scripts (resource) and references (resource) components.

What problem does it solve?

The Skill unit helps manage implementation plans with independent tasks by deploying fresh subagents for each task and conducting two-stage reviews.

Core Features & Use Cases

  • Independent Task Execution: Assigns a new subagent for each task, ensuring clear task boundaries and reduced context pollution.
  • Two-Stage Review Process: Facilitates a compliance review first and then a code quality review, leading to higher quality results.
  • Use Case: For teams that have well-defined implementation plans with multiple independent tasks and need a systematic approach to review and refine the code implementation.

Quick Start

To execute the plan using subagent-driven development, follow these steps: [Insert natural language instruction here]

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 implementation plans with independent subagent task management?

To execute implementation plans with independent subagent task management, assign a fresh subagent to each task. This ensures clear task boundaries and reduces context pollution for higher quality results.

What is the two-stage code review process for subagent-driven development?

The two-stage code review process for subagent-driven development involves a compliance review followed by a code quality review. This sequence ensures tasks meet specifications before refining the overall implementation.

Why does context pollution happen when executing multiple tasks with a single agent?

Context pollution happens because a single agent accumulates residual information from previous tasks. Deploying independent subagents for each task prevents this by maintaining clear task boundaries and fresh context.

Do I need subagent-prompting to manage task execution and specification compliance?

Yes, subagent-prompting is required to manage task execution and specification compliance. It provides the foundational prompts needed to direct different subagent types for reviews and implementation.

What's the best way to ensure specification compliance during code review?

The best way to ensure specification compliance during code review is using a two-stage process with independent reviewers. Facilitate a compliance review first, then conduct a separate code quality review.