skills.rest
AarushiShah
AarushiShahCOMMUNITY
Explore all skills by this author →
GitHub

subagent-driven-development

Executes implementation plans by dispatching fresh subagents per task with two-stage review.

Updated Mar 24, 2026
Search Tags:#tdd#code review#workflow automation#implementation plan#subagent#spec compliance#task orchestration
One-click install
npx skills add https://github.com/AarushiShah/coding-agents-databricks-apps --skill subagent-driven-development-aarushishah
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/AarushiShah/coding-agents-databricks-apps/tree/main/.claude/skills/subagent-driven-development
Command: npx skills add https://github.com/AarushiShah/coding-agents-databricks-apps --skill subagent-driven-development-aarushishah

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Executing a multi-task implementation plan manually risks context pollution, skipped reviews, and inconsistent quality across tasks. This Skill orchestrates plan execution by dispatching a fresh subagent for each task and enforcing a two-stage review (spec compliance, then code quality) after every task. ## Core Features & Use Cases - Fresh Subagent Per Task: Each task runs in an isolated subagent context, preventing cross-task confusion and context pollution. - Two-Stage Review Gates: A spec compliance reviewer verifies the code matches requirements exactly (nothing missing, nothing extra) before a code quality reviewer assesses maintainability and testing. - Prompt Templates Included: Ready-to-use templates for implementer, spec reviewer, and code quality reviewer subagents ensure consistent dispatching. - Use Case: You have a written implementation plan with 5 independent tasks. This Skill reads the plan once, creates a todo list, dispatches an implementer subagent per task, runs both review loops until approved, and finishes with a final whole-implementation code review. ## Quick Start Use subagent-driven development to execute the implementation plan in docs/plans/feature-plan.md task by task with reviews after 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 an implementation plan with AI subagents?▼

Read the plan once, extract all tasks with full text into a todo list, then dispatch a fresh implementer subagent per task with the complete task text and context. After each task, run a spec compliance review followed by a code quality review before marking it complete.

What is the difference between subagent-driven development and executing plans in a parallel session?▼

Subagent-driven development stays in the same session with no context switch and iterates faster without human-in-the-loop between tasks. Executing plans uses a separate parallel session, which suits workflows needing session isolation.

Why run spec compliance review before code quality review?▼

Spec compliance confirms the implementer built exactly what was requested, nothing missing or extra. Reviewing code quality first wastes effort if the implementation must change to match the spec, so quality review only starts after compliance passes.

When should I not use subagent-driven development?▼

Avoid it when tasks are tightly coupled and cannot be implemented independently, when no written plan exists yet, or when you need a parallel session instead of same-session execution. Brainstorm or write the plan first in those cases.

What happens when a reviewer subagent finds issues?▼

The same implementer subagent fixes the reported issues, then the reviewer re-reviews the changes. This loop repeats until the reviewer approves, and the task is never marked complete with open review issues.

Related Skills

Explore More Software Engineering Skills→
huangbaixunhuangbaixun
3

harness:subagent-driven-development

Dispatch isolated subagents to execute implementation plan tasks with spec and code quality reviews.

Community
Advanced
HexSleevesHexSleeves

staff-finishing-a-development-branch

Verify tests and present merge, pull request, keep, or discard options for a finished branch.

Community
Advanced
UniClipboardUniClipboard
1.5k

requesting-code-review

Dispatch a code-reviewer subagent to assess code changes between SHAs.

Official
Intermediate
lespacemanlespaceman
4

executing-plans

Execute written implementation plans in batches with human checkpoints.

Community
Advanced