skills.rest
Facostarr
FacostarrCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Assign fresh subagents per task and conduct two-stage reviews.

Updated Oct 29, 2025
Search Tags:#development workflow#task execution#subagent#task isolation#two-stage review
One-click install
npx skills add https://github.com/Facostarr/lagencesauvage.com2 --skill subagent-driven-development-facostarr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Facostarr/lagencesauvage.com2/tree/main/docs/skills/subagent-driven-development
Command: npx skills add https://github.com/Facostarr/lagencesauvage.com2 --skill subagent-driven-development-facostarr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires implementer-prompt.md, spec-reviewer-prompt.md, code-quality-reviewer-prompt.md, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the execution of independent tasks within a session, ensuring high-quality outcomes through precise task isolation and two-stage reviews.

Core Features & Use Cases

  • Task Isolation: Assigns a fresh subagent per task, maintaining isolation of context and history.
  • Two-Stage Review: Ensures compliance with specifications and code quality post-task completion.
  • Use Case: Ideal for development workflows where tasks are independent and require high-quality, fast iteration.

Quick Start

To initiate Subagent-Driven Development, first read the plan, extract all tasks, and note context, then create a TodoWrite list.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I isolate context and history when executing independent development tasks in a single session?▼

Task isolation is achieved by assigning a fresh subagent per task, ensuring context and history remain independent throughout the development workflow. This prevents cross-task contamination and maintains clean execution boundaries.

What is the best way to enforce code quality and spec compliance during task execution?▼

Two-stage reviews enforce compliance with specifications and code quality post-task completion. This approach uses specific prompt templates for spec reviewers and code quality reviewers to evaluate task outcomes independently.

How do I start subagent-driven development for independent task execution?▼

To start subagent-driven development, read the plan, extract all tasks, note the context, and create a TodoWrite list. This initiates the workflow by organizing tasks before assigning fresh subagents.

Do I need specific prompt templates to use subagent-driven development?▼

Yes, this workflow requires specific prompt templates for implementer, spec reviewer, and code quality reviewer subagents. These templates drive the task execution and the two-stage review process.

When should I not use a two-stage subagent review for development workflows?▼

This approach suits independent, high-quality, fast iteration tasks but may not fit highly interdependent tasks. It requires specific prompt templates and task isolation to function correctly.

Related Skills

Explore More Software Engineering Skills→
guanyangguanyang
947

subagent-driven-development

Execute implementation plans by dispatching subagents for tasks and reviewing spec compliance and code quality.

Community
Advanced
brmatolabrmatola

requesting-code-review

Dispatch a code-reviewer subagent to review changes before merging.

Community
Basic
redsub-captainredsub-captain
2

redsub-execute

Execute implementation plan tasks sequentially with subagent dispatch and two-stage review.

Community
Advanced
HarriesHarries

subagent-driven-development

Dispatch fresh subagents for each task and run two-stage reviews.

Community
Advanced