skills.rest
makerjackie
makerjackieCOMMUNITY
Explore all skills by this author →
𝕏@maker_jackieGitHub

subagent-driven-development

Dispatch fresh subagents to execute independent tasks with two-stage reviews.

1|Updated Feb 20, 2026
Search Tags:#automation#subagent#software-development#code-review#spec-compliance
One-click install
npx skills add https://github.com/makerjackie/jackie-skills-starter --skill subagent-driven-development-makerjackie
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/makerjackie/jackie-skills-starter/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/makerjackie/jackie-skills-starter --skill subagent-driven-development-makerjackie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual implementation of plans often suffers from context contamination, missed review steps, and inefficient handling of independent tasks, leading to low quality and slow iteration.

Core Features & Use Cases

  • Fresh Subagent per Task: Each task is delegated to a new subagent to avoid context pollution.
  • Two‑Stage Review: Automatic spec‑compliance review followed by code‑quality review after every task.
  • Task Extraction & Management: Reads a plan, extracts all tasks, creates TodoWrite entries, and coordinates the full workflow.
  • Integration with Superpowers: Works with git worktrees, plan writing, code review, and branch finishing skills to provide an end‑to‑end development pipeline.
  • Use Case: Apply to a feature plan where tasks are independent, and you want high‑quality code delivered within the same session without manual hand‑offs.

Quick Start

Ask the AI: “Use subagent‑driven development to execute my plan file ‘feature‑plan.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 automate spec compliance and code quality reviews for independent tasks?▼

Automating spec compliance and code quality reviews requires dispatching fresh subagents per task, applying a two-stage review process where each task undergoes spec review followed by code-quality validation before completion.

What is subagent-driven development and when should I use it for software development?▼

Subagent-driven development is a workflow that executes implementation plans by delegating each independent task to a new subagent to avoid context contamination. Use it for same-session feature plans where tasks need automated spec and code-quality validation.

How do I execute a feature plan file using subagents?▼

To execute a feature plan, instruct the AI to use subagent-driven development on your plan file. The system reads the plan, extracts all tasks, creates TodoWrite entries, and coordinates dispatching fresh subagents to implement and review each task.

Does subagent-driven development work with git worktrees and branch finishing?▼

Yes, subagent-driven development integrates with git worktrees, plan writing, code review, and branch finishing skills, providing an end-to-end development pipeline from task extraction through deployment without manual hand-offs.

Why does manual implementation of independent tasks lead to context pollution?▼

Manual implementation causes context pollution because the same agent handles multiple tasks sequentially, contaminating the context window. Dispatching fresh subagents per task isolates the context, ensuring clean execution and consistent spec compliance.

Can I use subagent-driven development for dependent tasks in the same session?▼

Subagent-driven development is designed for largely independent tasks within same-session workflows. If your tasks have heavy dependencies, the fresh subagent approach may lack the shared context needed for complex inter-task coordination.

Related Skills

Explore More Software Engineering Skills→
galangryandanagalangryandana
20

subagent-driven-development

Dispatch fresh subagents to execute independent implementation tasks with two-stage reviews.

Community
Advanced
wsxwj123wsxwj123
7

requesting-code-review

Automate structured code reviews before merging to main branches.

Community
Intermediate
danielcopperdanielcopper
3

pr-review

Automate Azure DevOps pull request reviews with parallel code-analysis agents and empirical validation.

Community
Advanced
obraobra
41

Subagent-Driven Development

Dispatch a fresh subagent for each task and trigger code review after completion.

Community
Basic