skills.rest
do-zoo
do-zooCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

subagent-driven-development

Execute implementation plans by dispatching fresh subagents for isolated tasks.

Updated Aug 27, 2026
Search Tags:#automation#subagents#code-quality#prompt-engineering#plan-execution#two-stage-review#task-dispatch
One-click install
npx skills add https://github.com/do-zoo/match-screening-cisc --skill subagent-driven-development-do-zoo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/do-zoo/match-screening-cisc/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/do-zoo/match-screening-cisc --skill subagent-driven-development-do-zoo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates complex implementation workflows by delegating tasks to fresh subagents, ensuring isolated contexts and rapid iteration.

Core Features & Use Cases

  • Fresh subagent per task with isolated context to prevent context leakage
  • Two-stage review workflow after each task: spec compliance, then code quality
  • Parallel, session-spanning task execution without cross-task context pollution

Quick Start

Provide your implementation plan and trigger the subagent-driven workflow to execute each task with fresh subagents.

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 with isolated contexts?▼

Automating implementation plan execution involves dispatching fresh subagents to handle decoupled tasks, ensuring isolated contexts prevent leakage during rapid iteration across a single session.

What is a two-stage review workflow for code quality and spec compliance?▼

A two-stage review workflow evaluates task completion by first verifying spec compliance using a dedicated reviewer prompt, then assessing code quality with a separate reviewer prompt.

How do I prevent context pollution when running parallel coding tasks?▼

Preventing context pollution when running parallel coding tasks requires dispatching independent subagents per task, maintaining isolated contexts without cross-task interference throughout session-spanning execution.

Can I use prompt engineering to coordinate task dispatch for multiple subagents?▼

Prompt engineering coordinates task dispatch for multiple subagents by using dedicated prompts for the implementer, spec reviewer, and code quality reviewer to structure execution.

What are the limitations of using fresh subagents for task execution?▼

Fresh subagents for task execution require multiple decoupled tasks to be effective; tightly coupled tasks in a single session may not benefit from isolated contexts and rapid iteration.

Related Skills

Explore More Software Engineering Skills→
rafaelromaorafaelromao
5

sandman-plan

Generate an execution-ready plan from issue context and code exploration.

Community
Advanced
haleyrchaleyrc
2

feature-merge

Squash merge feature branch commits into main with a Conventional Commit message.

Community
Intermediate
LeonardoTan19LeonardoTan19
2

requesting-code-review

Dispatch a code-reviewer subagent to validate completed work against requirements.

Community
Advanced
roderikroderik
2

subagent-driven-development

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

Community
Advanced