skills.rest
tridigitals
tridigitalsCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Dispatch specialized subagents for each task with two-stage reviews.

Updated Feb 9, 2026
Search Tags:#automation#subagents#code-review#plan-execution#task-dispatch#spec-review#isolated-context
One-click install
npx skills add https://github.com/tridigitals/ispmanagement --skill subagent-driven-development-tridigitals
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/tridigitals/ispmanagement/tree/main/.roo/skills/subagent-driven-development
Command: npx skills add https://github.com/tridigitals/ispmanagement --skill subagent-driven-development-tridigitals

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-Driven Development enables executing implementation plans by dispatching fresh subagents for each task, with isolated context and built-in two-stage reviews to improve quality and speed.

Core Features & Use Cases

  • Fresh subagent per task to avoid context leakage and enable parallelism.
  • Two-stage review: spec compliance first, then code quality.
  • Automated workflows using predefined prompts and templates for implementer, spec reviewer, and code quality reviewer.
  • Suitable for complex, multi-step development plans and iterative experimentation.

Quick Start

Begin by dispatching an implementer subagent for Task N and follow the two-stage review workflow.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I orchestrate subagents to execute a multi-step development plan?▼

Orchestrate subagents by dispatching a fresh, specialized subagent for each task in a plan with isolated context, enabling structured question-asking and automated two-stage reviews to improve implementation speed.

What is the best way to automate code review during plan execution?▼

Automate code review during plan execution using a built-in two-stage workflow that first verifies spec compliance and then checks overall code quality through predefined prompt templates for each subagent.

Can I use isolated context to prevent context leakage when dispatching parallel implementation tasks?▼

Yes, isolated context prevents context leakage by assigning a fresh subagent to each task, which enables safe parallelism and ensures that sequential or parallel implementation tasks remain independently scoped.

How does two-stage spec review work for subagent-driven task dispatch?▼

Two-stage spec review works by first deploying a spec reviewer subagent to verify requirements compliance, followed by a code quality reviewer subagent that performs final checks before structured reporting.

Do I need predefined prompt templates to structure subagent task execution?▼

Yes, predefined prompt templates are needed to structure subagent task execution, providing the automated workflows required for the implementer, spec reviewer, and code quality reviewer roles.

When should I not use subagents for executing iterative development tasks?▼

You should avoid subagent-driven development for simple, single-step tasks that do not benefit from isolated context, parallel execution, or the overhead of structured two-stage spec and code quality reviews.

Related Skills

Explore More Software Engineering Skills→
xlelibertyxleliberty

subagent-driven-development

Orchestrates multi-task implementation plans by dispatching specialized subagents for development and review.

Community
Advanced
koki3141koki3141
2

checkpoint-manager

Create, verify, and list git snapshot workflow checkpoints.

Community
Intermediate
yckkkkyckkkk
1

subagent-driven-development

Dispatch each task to a fresh subagent and enforce two-stage reviews.

Community
Advanced
LisztVanLisztVan
2

dispatching-parallel-agents

Delegate independent debugging tasks to isolated agents for parallel execution.

Community
Advanced