subagent-driven-development

Dispatch independent repo-change tasks to subagents from an implementation plan.

32|1|Updated May 19, 2026
One-click install
npx skills add https://github.com/woodfishhhh/EZ_math_model --skill subagent-driven-development-woodfishhhh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/woodfishhhh/EZ_math_model/tree/main/skills/ez-math-model/tools/subagent-driven-development
Command: npx skills add https://github.com/woodfishhhh/EZ_math_model --skill subagent-driven-development-woodfishhhh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you convert a written implementation plan into coordinated, verifiable development tasks for extending EZ_math_model, reducing missed steps and conflicting edits.

Core Features & Use Cases

  • Plan-to-task dispatching: Breaks an implementation plan into independent sub-tasks with clear ownership and acceptance criteria.
  • Guardrails for repo modifications: Helps ensure write scopes are non-overlapping and that task dependencies are resolved or handled by falling back to sequential execution.
  • EZMM-focused mapping: Targets common extensions like adding algorithms, adding tool skills, or executing an existing plan file.

Quick Start

In the chat, ask it to extend EZ_math_model by following your plan file and dispatch the independent tasks to subagents with explicit acceptance criteria.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I turn an implementation plan into verifiable repository changes?

To turn an implementation plan into repository changes, you can dispatch independent sub-tasks to subagents with explicit acceptance criteria, ensuring write scopes do not overlap and dependencies are resolved.

What is the best way to execute a multi-step plan for extending a math model algorithm?

Executing a multi-step plan for extending an algorithm involves breaking the plan into independent repo-change tasks and dispatching them to subagents, falling back to sequential execution if task dependencies conflict.

How do I dispatch independent development tasks to subagents without causing conflicting edits?

Dispatching independent development tasks safely requires validating task independence, checking for dependency conflicts, and applying non-overlapping write scopes before assigning the repo changes to subagents.

Can I use subagent task dispatching for adding new tool skills to an existing repository?

Yes, you can use subagent task dispatching for adding new tool skills by mapping the extension steps from your plan file into independent tasks with clear boundaries and assigning them to subagents.

What happens when task dependencies conflict during plan execution?

When task dependencies conflict during plan execution, the system falls back to sequential execution to maintain safe repo modifications and ensure all acceptance criteria are met without overlapping edits.