subagent-driven-development

Distribute plan execution across autonomous subagents with two-stage reviews.

Updated Nov 8, 2024
One-click install
npx skills add https://github.com/cqkxxc/cqkxxc.github.io --skill subagent-driven-development-cqkxxc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/cqkxxc/cqkxxc.github.io/tree/main/.trae/skills/subagent-driven-development
Command: npx skills add https://github.com/cqkxxc/cqkxxc.github.io --skill subagent-driven-development-cqkxxc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Distributes plan execution across autonomous subagents to improve speed and quality.

Core Features & Use Cases

  • Fresh subagent per task to prevent context leakage and enable parallel work within a single session.
  • Two-stage review after each task: spec compliance review first, then code quality review.
  • Per-task workflow with clear responsibilities while maintaining overall session coherence.
  • Provides standardized prompts and templates to guide delegation and reviews.

Quick Start

Dispatch a new subagent for each task in your current plan and follow the two-stage review process after 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 distribute plan execution across autonomous subagents to improve development workflow speed?

To distribute plan execution, dispatch a fresh subagent for each independent task within your session, then apply a two-stage review process checking spec compliance before code quality to ensure correctness and prevent context leakage.

What is the two-stage review process for ai-assisted code generation?

The two-stage review process evaluates autonomous subagent output by first checking spec compliance to verify requirements are met, then performing a code quality review to ensure implementation standards before finalizing the task.

How do I prevent context leakage when automating development workflows with multiple independent tasks?

Prevent context leakage by dispatching a fresh subagent for each independent task, maintaining per-task workflows with standardized prompts and templates to guide delegation while preserving overall session coherence.

Can I use subagent-driven development for iterative spec compliance reviews within a single session?

Yes, subagent-driven development applies to sessions with independent tasks requiring iterative spec and code quality reviews, using structured prompts and standardized templates to guide delegation and maintain coherence.

What's the best way to structure prompts for autonomous subagents handling plan execution?

Structure prompts using standardized templates that establish clear responsibilities for per-task workflows, enabling autonomous subagents to execute plans while maintaining overall session coherence through guided delegation.

Does subagent-driven development work for parallel development tasks in the same session?

Yes, subagent-driven development enables parallel work within a single session by dispatching fresh subagents per task, applying two-stage reviews after each task to ensure spec compliance and code quality.