subagent-driven-development

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

Updated Dec 30, 2025
One-click install
npx skills add https://github.com/bluefishs/CK_Missive --skill subagent-driven-development-bluefishs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/bluefishs/CK_Missive/tree/main/.claude/skills/_shared/shared/superpowers/subagent-driven-development
Command: npx skills add https://github.com/bluefishs/CK_Missive --skill subagent-driven-development-bluefishs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Use when executing implementation plans with independent tasks in the current session. This Skill orchestrates plan execution by dispatching a fresh subagent per task and applying a two-stage review process after each task to ensure spec compliance and code quality.

Core Features & Use Cases

  • Fresh subagent per task with isolation to prevent context pollution.
  • Two-stage review after each task: spec compliance review followed by code quality review.
  • Structured task orchestration for linear or parallel sessions with clear handoffs and clear completion criteria.

Quick Start

Execute an implementation plan by dispatching per-task subagents and applying two-stage reviews for each task to drive high-quality outcomes.

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent context pollution when executing implementation plans with independent tasks?

To prevent context pollution during implementation plan execution, dispatch a fresh subagent for each task. This isolation ensures rapid iteration without accumulating irrelevant context across independent tasks.

What is the best way to automate spec compliance and code quality reviews during task dispatch?

Automating spec compliance and code quality reviews requires a two-stage review process after each task. A specialized spec reviewer verifies requirements before a code quality reviewer checks the implementation.

How does a two-stage review process work for subagent task orchestration?

A two-stage review process works by applying sequential automated handoffs after a task subagent finishes. The implementation first undergoes a spec compliance review, followed by a separate code quality review before merging.

When do I need to use fresh subagents for workflow automation?

You need fresh subagents for workflow automation when executing sessions with largely independent tasks. This approach suits development cycles requiring rapid iteration and strict context isolation to maintain execution efficiency.

Can I use subagent-driven task dispatch for parallel implementation sessions?

Yes, subagent-driven task dispatch supports structured orchestration for both linear and parallel implementation sessions. It provides clear handoffs and defined completion criteria to manage independent tasks effectively.