skills.rest
greglamb
greglambCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

subagent-driven-development

Execute implementation plans via isolated subagents with two-stage review gates.

1|Updated Mar 20, 2026
Search Tags:#testing#code review#software development#subagents#task delegation#implementation plans#specification compliance
One-click install
npx skills add https://github.com/greglamb/macos-name-tag-app --skill subagent-driven-development-greglamb
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/greglamb/macos-name-tag-app/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/greglamb/macos-name-tag-app --skill subagent-driven-development-greglamb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents implementation plans from becoming inconsistent or poorly reviewed by coordinating isolated subagents and enforcing structured quality gates for every task.

Core Features & Use Cases

  • Task Delegation: Dispatch a fresh implementation subagent for each independent task with focused context and clear requirements.
  • Two-Stage Reviews: Require specification compliance review before code quality review, with fix-and-review loops for unresolved issues.
  • Workflow Coordination: Track task status, handle implementer questions or blockers, and conduct a final review after all tasks are complete.
  • Use Case: When executing a multi-task feature plan in one session, use this Skill to delegate each task independently while ensuring every change meets the specification and maintainability standards.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan in the current session with isolated implementers and two-stage reviews for 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 execute a multi-task implementation plan with isolated subagents?▼

To execute an implementation plan with isolated subagents, you dispatch a fresh implementer for each independent task and enforce two-stage specification and code quality review gates before integration.

What is a structured review gate in software development task delegation?▼

A structured review gate in task delegation is a mandatory quality checkpoint where a dedicated reviewer checks specification compliance and code quality, triggering iterative remediation loops for any identified issues before proceeding.

How do I ensure specification compliance when delegating coding tasks to subagents?▼

You ensure specification compliance by running a dedicated specification review immediately after implementation, requiring the subagent to fix deviations through iterative remediation before advancing to code quality review.

Do I need a written implementation plan before starting subagent-driven development?▼

Yes, subagent-driven development requires a written implementation plan and task-specific context upfront to provide focused requirements for each isolated implementer and to track task status throughout the session.

Can I use isolated subagents for independent software engineering tasks in a single session?▼

Yes, you can use isolated subagents for independent software engineering tasks in a single session by dispatching a fresh implementer for each task and coordinating workflow through structured review gates and status tracking.

What is the best way to coordinate code quality reviews across multiple delegated tasks?▼

The best way to coordinate code quality reviews across delegated tasks is to enforce a two-stage review process per task, followed by a final comprehensive review after all implementation tasks are complete.

Related Skills

Explore More Software Engineering Skills→
roderikroderik
2

subagent-driven-development

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

Community
Advanced
DYAI2025DYAI2025
3

executing-plans

Execute implementation plans in batches with review checkpoints and task verification.

Community
Basic
bobmatnycbobmatnyc
146

Requesting Code Review

Dispatch a code-reviewer subagent to review changes against plans and requirements.

Community
Basic
rubenslivrubensliv
15

polars

Process large datasets with lazy-evaluated DataFrame transformations in Python and Rust.

Community
Advanced