skills.rest
Cyapstaye
CyapstayeCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Orchestrate multi-step implementation plans by delegating tasks to subagents.

9|Updated Jul 1, 2026
Search Tags:#workflow#tdd#implementation#delegation#parallel#subagent
One-click install
npx skills add https://github.com/Cyapstaye/Adame_ver.open --skill subagent-driven-development-cyapstaye
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Cyapstaye/Adame_ver.open/tree/main/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/Cyapstaye/Adame_ver.open --skill subagent-driven-development-cyapstaye

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill solves the issue of context pollution and quality degradation in long-running agent tasks by enforcing a modular, subagent-based execution workflow with rigorous validation gates.

Core Features & Use Cases

  • Modular Execution: Dispatches fresh, focused subagents for individual tasks to maintain clean context and state.
  • Two-Stage Review: Implements mandatory spec compliance and code quality reviews for every task to ensure high-fidelity output.
  • Use Case: Use this skill to implement a multi-file feature plan where each component requires TDD, spec verification, and quality assurance before final integration.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located in docs/plans/feature-plan.md by dispatching subagents for each task.

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 multi-step implementation plans without context pollution?▼

Execute multi-step implementation plans by delegating individual tasks to fresh, focused subagents. This modular workflow prevents context pollution and quality degradation in long-running agent tasks.

Does subagent-driven development enforce TDD and spec compliance for each task?▼

Yes, subagent-driven development applies systematic TDD and implements mandatory spec compliance and code quality reviews for every task to ensure high-fidelity output before integration.

How do I manage a multi-file feature plan using autonomous subagents?▼

You can manage a multi-file feature plan by providing a structured plan file. The skill orchestrates the development lifecycle by dispatching subagents for each component using terminal and file system tools.

What is the best way to maintain code quality in parallel agent workflows?▼

The best way to maintain code quality in parallel agent workflows is to use a two-stage review system with rigorous validation gates, verifying both spec compliance and code quality for every dispatched task.

Do I need a structured plan file to use subagent-driven development?▼

Yes, you need a structured plan file, such as docs/plans/feature-plan.md. The skill requires this file to orchestrate the execution of the multi-step implementation plan via subagents.

Why does long-running agent task quality degrade and how to prevent it?▼

Long-running agent task quality degrades due to context pollution. You can prevent this by enforcing a modular, subagent-based execution workflow that dispatches fresh subagents for individual tasks with validation gates.

Related Skills

Explore More Software Engineering Skills→
WesleyMFrederickWesleyMFrederick

writing-plans

Generate implementation plans with exact file paths, code samples, and tests.

Community
Basic
patrykk21patrykk21

shell

Execute literal shell commands directly within the AI interface.

Community
Basic
hanibalskhanibalsk
3

subagent-driven-development

Execute implementation plans by dispatching fresh subagents with code reviews between tasks.

Community
Advanced
hainamchunghainamchung
54

subagent-driven-development

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

Community
Advanced