subagent-driven-development

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

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/robkisk/coding-agents-databricks-app --skill subagent-driven-development-robkisk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/robkisk/coding-agents-databricks-app/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/robkisk/coding-agents-databricks-app --skill subagent-driven-development-robkisk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the execution of complex implementation plans by breaking them down into independent tasks, each handled by a fresh subagent with a rigorous two-stage review process.

Core Features & Use Cases

  • Task Decomposition: Executes plans by dispatching a dedicated subagent for each task.
  • Two-Stage Review: Implements a spec compliance review followed by a code quality review for every task.
  • Iterative Refinement: Facilitates rapid iteration through automated review and fix loops.
  • Use Case: When you have a detailed plan to add a new feature, this Skill ensures each part of the feature is implemented correctly, reviewed for adherence to the spec, and then checked for overall code quality before moving to the next part.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at ./plans/new-feature.md.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I execute an implementation plan by breaking it down into independent tasks?

Subagent-driven development executes implementation plans by dispatching a dedicated subagent for each task, ensuring rigorous spec compliance and code quality through a two-stage review process within a single session.

What is the two-stage review process for iterative development?

The two-stage review process first checks spec compliance for each completed task, then evaluates overall code quality, facilitating rapid iteration through automated review and fix loops before moving to the next task.

Can I use subagents to handle complex feature plans with multiple independent tasks?

Yes, this approach orchestrates complex feature plans by dispatching a fresh subagent for each independent task, managing task iteration, question handling, and final code review within a single session for efficient development cycles.

How do I automate code review and spec compliance checks during development?

Automated code review and spec compliance checks are handled by dispatching subagents that implement tasks and undergo a two-stage review, enabling iterative refinement through automated review and fix loops.

When should I use subagent-driven development instead of sequential task execution?

Use subagent-driven development when executing detailed implementation plans for new features, as it ensures each part is implemented correctly with rigorous two-stage review and iterative refinement before proceeding to the next task.