Agent-Skills.md

Agent Skills: Subagent-Driven Development

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

UncategorizedID: zpankz/mcp-skillset/subagent-driven-development

Repository

zpankz/mcp-skillset
Zpankz
12

Install this agent skill to your local

pnpm dlx add-skill https://github.com/Zpankz/mcp-skillset/tree/HEAD/subagent-driven-development

Skill Files

Browse the full folder contents for subagent-driven-development.

Download Skill

Loading file tree…

subagent-driven-development/SKILL.md

Skill Metadata

Name
subagent-driven-development
Description
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Subagent-Driven Development

Create and execute plan by dispatching fresh subagent per task or issue, with code and output review after each or batch of tasks.

Core principle: Fresh subagent per task + review between or after tasks = high quality, fast iteration.

Overview

Executing Plans through agents:

  • Same session (no context switch)
  • Fresh subagent per task (no context pollution)
  • Code review after each or batch of task (catch issues early)
  • Faster iteration (no human-in-loop between tasks)

Supported Types of Execution

Sequential Execution

When tasks are tightly coupled and need to be executed in order.

  • Dispatch one agent per task or issue
  • Let it work sequentially
  • Review the output and code after each task or issue

Parallel Execution

When you have multiple unrelated tasks (different files, different subsystems, different bugs).

  • Dispatch one agent per independent problem domain
  • Let them work concurrently
  • Overall review after all tasks are completed

Parallel Investigation

Special case for multiple unrelated failures that can be investigated without shared state or dependencies.

Progressive Loading

L2 Content (loaded when sequential execution process needed):

L3 Content (loaded when parallel execution or investigation needed):