skills.rest
ollieb89
ollieb89COMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch AI subagents for atomic tasks with two-stage reviews.

Updated Feb 18, 2026
Search Tags:#code review#prompt engineering#ai development#iterative development#task execution#subagent
One-click install
npx skills add https://github.com/ollieb89/openrepo --skill subagent-driven-development-ollieb89
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/ollieb89/openrepo/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/ollieb89/openrepo --skill subagent-driven-development-ollieb89

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the implementation of development plans by breaking them into independent tasks, each handled by a fresh AI subagent with rigorous, multi-stage review processes.

Core Features & Use Cases

  • Task Decomposition: Executes complex plans by dispatching individual AI agents for each atomic task.
  • Two-Stage Review: Implements a robust review process including spec compliance and code quality checks after each task.
  • Iterative Improvement: Facilitates rapid iteration through automated review loops and subagent-driven fixes.
  • Use Case: Developing a new feature involves multiple distinct steps like setting up a database schema, implementing API endpoints, and writing frontend components. This Skill ensures each step is completed correctly and to standard before moving to the next.

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 automate iterative development with AI subagents for complex software plans?▼

Iterative development with AI subagents automates complex software plans by dispatching independent AI agents for each atomic task. It manages task execution and subagent communication within a single session to ensure efficient development cycles.

What is the two-stage code review process in AI-driven development?▼

The two-stage code review process enforces spec compliance checks followed by code quality checks after each task completion. This ensures every atomic step meets project standards before the subagent-driven development loop proceeds to the next iteration.

How do I execute a development plan by breaking it into independent AI tasks?▼

You execute a development plan by dispatching a fresh AI subagent for each atomic task, such as setting up database schemas or implementing API endpoints. The skill orchestrates these independent tasks and manages automated review loops for iterative improvement.

Can I use prompt engineering to manage subagent communication during task execution?▼

Prompt engineering is used to manage subagent communication and task execution within a single session. The skill orchestrates these independent AI agents, handling their interactions and routing fixes through automated review loops.

What are the limitations of using subagent-driven development for feature implementation?▼

Subagent-driven development operates within a single session and requires breaking plans into atomic tasks. If a task cannot be isolated or requires cross-task state sharing, the independent subagent dispatch and review loop may face execution constraints.

Does subagent-driven development work without external dependencies?▼

Subagent-driven development works without external dependencies, using built-in scripts and references. It orchestrates AI agents and manages review loops internally, requiring only a development plan file to begin task execution.

Related Skills

Explore More Software Engineering Skills→
caobingshengcaobingsheng
1

subagent-driven-development

Dispatch independent subagents for each implementation task with two-stage reviews.

Community
Advanced
raroqueraroque
925

vibe-security

Audit codebases for security vulnerabilities in AI-generated code.

Community
Advanced
roundpilotroundpilot
53

subagent-driven-development

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

Community
Advanced
Come0520Come0520

subagent-driven-development

Orchestrate implementation plans by dispatching AI subagents for tasks and reviews.

Community
Advanced