skills.rest
jokken79
jokken79COMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch fresh subagents per task with two-stage reviews.

1|Updated Dec 15, 2025
Search Tags:#automation#implementation#subagent#prompt-engineering#plan-execution#timeliness#twostage-review
One-click install
npx skills add https://github.com/jokken79/YuKyuDATA-app1.0v --skill subagent-driven-development-jokken79
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/jokken79/YuKyuDATA-app1.0v/tree/main/.agent/skills/subagent-driven-development
Command: npx skills add https://github.com/jokken79/YuKyuDATA-app1.0v --skill subagent-driven-development-jokken79

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fresh subagents per task enable executing complex implementation plans within a single session, ensuring isolated context and structured reviews to improve quality and speed.

Core Features & Use Cases

  • Fresh subagent per task to maintain context isolation
  • Two-stage review after each task: spec compliance first, then code quality
  • Self-review before reporting back to tighten quality
  • Predefined prompts for implementer, spec reviewer, and code-quality reviewer
  • Works in a single session with sequential or parallel task flow depending on plan

Quick Start

Initialize a plan and dispatch a new subagent for each task using the provided prompts.

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 plan execution with isolated context for each task?▼

You can automate plan execution by dispatching a fresh subagent per task. This maintains context isolation, enabling rapid iteration and structured two-stage reviews within a single conversation session.

What is the best way to maintain code quality during rapid implementation?▼

Maintaining code quality during rapid implementation requires a two-stage review process. A spec compliance review is followed by a code quality review, incorporating self-review loops to tighten the final output.

How do I set up prompts for spec and code reviewers in a subagent workflow?▼

Setting up reviewer prompts involves defining predefined templates for the implementer, spec reviewer, and code-quality reviewer. These structured prompts control the workflow and ensure completeness across independent tasks.

Can I execute complex implementation plans within a single session?▼

Yes, you can execute complex implementation plans within a single session. Fresh subagents handle sequential or parallel task flows, ensuring isolated context and structured reviews to improve speed.

Does subagent-driven development work for independent tasks only?▼

Subagent-driven development is applicable to sessions where tasks are mostly independent. It requires structured task prompts and a controlled workflow to ensure completeness and quality across rapid iterations.

When should I not use fresh subagents for task implementation?▼

You should avoid using fresh subagents for task implementation when tasks are highly dependent on each other. The approach relies on isolated context, making it unsuitable for tightly coupled workflows without structured prompts.

Related Skills

Explore More Software Engineering Skills→
tridigitalstridigitals

subagent-driven-development

Dispatch specialized subagents for each task with two-stage reviews.

Community
Advanced
gmliaogmliao
1

executing-plans

Execute implementation plans in batches with review checkpoints and progress reporting.

Community
Basic
sbalagan22sbalagan22

subagent-driven-development

Delegate each task to a fresh subagent with two-stage spec and code-quality reviews.

Community
Advanced
mor-duongmhmor-duongmh
3

subagent-driven-development

Delegate each task to a fresh subagent with isolated context and two-stage reviews.

Community
Intermediate