implement-feature

Orchestrate parallel coder agent waves with code review gates for feature specs.

426|199|Updated Aug 13, 2025
One-click install
npx skills add https://github.com/leonvanzyl/agentic-coding-starter-kit --skill implement-feature-leonvanzyl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: implement-feature
Source: https://github.com/leonvanzyl/agentic-coding-starter-kit/tree/main/.agents/skills/implement-feature
Command: npx skills add https://github.com/leonvanzyl/agentic-coding-starter-kit --skill implement-feature-leonvanzyl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate parallel feature implementation by coordinating coder subagents that work in waves and require code review gates between waves.

Core Features & Use Cases

  • Orchestrates spec-driven feature work by dispatching coder agents in parallel waves
  • Performs per-wave code reviews and fix loops to ensure integration
  • Supports resumable progress by picking up where a spec left off

Quick Start

Create a specs/{feature}/ directory with README.md, requirements.md, and task files, then run this skill to start the first wave.

Frequently Asked Questions about implement-feature

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

FAQPage Schema
How do I coordinate parallel feature implementation using coder agents?

Parallel feature implementation is coordinated by dispatching coder subagents wave-by-wave, applying code review gates between each wave to ensure integration before proceeding to the next set of tasks.

What is a spec-driven workflow for orchestrating feature development?

A spec-driven workflow organizes feature requirements into a specs directory containing README, requirements, and task files, allowing an orchestrator to dispatch agents for parallel execution and track progress resumably across sessions.

How do I start parallel feature implementation with a spec directory?

To start parallel feature implementation, create a specs/{feature}/ directory containing README.md, requirements.md, and task files, then run the orchestrator to automatically dispatch the first wave of coder agents.

Can I resume feature implementation progress if a session is interrupted?

Yes, resumable progress is supported by picking up exactly where the spec left off, allowing the orchestration of ready waves to continue across different sessions without losing completed work.

Does the feature implementation orchestrator write code directly?

No, the orchestrator does not write code directly; it coordinates task delegation, performs per-wave code reviews, and manages fix loops while coder agents handle the actual implementation.

What's the best way to ensure code integration during parallel agent execution?

Code integration during parallel execution is ensured by applying per-wave code review gates and fix loops between waves, verifying that all coder agents' outputs meet requirements before proceeding.