skills.rest
kk20300113-png
kk20300113-pngCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

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

Updated May 9, 2026
Search Tags:#code quality#code review#software development#task automation#spec compliance#implementation plans#subagent workflow
One-click install
npx skills add https://github.com/kk20300113-png/my-claude-skills --skill subagent-driven-development-kk20300113-png
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/kk20300113-png/my-claude-skills/tree/main/subagent-driven-development
Command: npx skills add https://github.com/kk20300113-png/my-claude-skills --skill subagent-driven-development-kk20300113-png

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the slow, error-prone process of manually executing implementation plans, reducing context pollution and missed requirements or quality issues that come with switching between tasks in a single session.

Core Features & Use Cases

  • Per-task subagent dispatch: Assigns a fresh, focused subagent to each independent task with full context, no inherited session history to cause confusion.
  • Two-stage review workflow: Runs spec compliance review first, then code quality review after each task to catch missing requirements and implementation issues early.
  • Use Case: Use this when you have a detailed implementation plan with independent tasks and want to execute them in the current session without manual intervention between steps, ensuring each task meets specs and quality standards before moving on.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan in your project by dispatching a fresh subagent for each independent task with two-stage review after each 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 implementation plan execution without manual intervention between tasks?▼

Automating implementation plan execution requires dispatching a fresh subagent to each independent task with full context, running two-stage spec and code quality reviews, and triggering iterative fix loops to ensure each task meets requirements before proceeding.

Why does context pollution occur when executing multiple development tasks in a single session?▼

Context pollution occurs because a single session inherits previous task history, causing confusion. Dispatching a fresh, focused subagent for each independent task eliminates inherited session history and ensures focused execution without context bleed.

What is the best way to run automated spec compliance and code quality reviews after each implementation task?▼

The best way to run automated reviews is using a two-stage workflow: execute spec compliance review first to catch missing requirements, then run code quality review to identify implementation issues, followed by iterative fix loops to resolve any detected problems.

Can I use subagent workflows for software development tasks requiring isolated context per task?▼

Yes, subagent workflows support software development tasks requiring isolated context per task. The workflow assigns a fresh subagent with full context to each independent task, ensuring no inherited session history causes confusion during continuous execution.

When should I not use subagent-driven development for task automation?▼

You should not use subagent-driven development when your implementation plan lacks independent tasks or when tasks require shared session history. This approach applies only to workflows with decoupled tasks requiring isolated context per task and continuous execution.

How do subagent workflows handle iterative fix loops for code quality issues?▼

Subagent workflows handle iterative fix loops by running a two-stage review after each task completion. If spec compliance or code quality reviews identify issues, the workflow triggers iterative fixes to ensure each implementation task meets requirements before proceeding to the next.

Related Skills

Explore More Software Engineering Skills→
kyo0221kyo0221

subagent-driven-development

Dispatch isolated subagents for multi-task implementation plans with mandatory two-stage reviews.

Community
Advanced
oimiragieooimiragieo
36

evaluator

Evaluate agent performance, rule compliance, and workflow quality across task datasets.

Community
Advanced
roundpilotroundpilot
53

subagent-driven-development

Dispatch subagents to execute development plans with two-stage reviews.

Community
Advanced
roderikroderik
2

subagent-driven-development

Dispatch fresh subagents per task to execute implementation plans with two-stage reviews.

Community
Advanced