implement-feature

Orchestrates wave-based parallel coder agents with code-review gates for feature specs.

Updated May 14, 2026
One-click install
npx skills add https://github.com/LeroyAdonis/vector --skill implement-feature-leroyadonis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: implement-feature
Source: https://github.com/LeroyAdonis/vector/tree/main/.agents/skills/implement-feature
Command: npx skills add https://github.com/LeroyAdonis/vector --skill implement-feature-leroyadonis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Orchestrate the parallel implementation of a feature specification by dispatching coder agents wave-by-wave with code review gates between waves. The orchestrator does not write code itself; it coordinates tasks, context, and reviews to ensure quality while enabling scalable collaboration.

Core Features & Use Cases

  • Wave-based orchestration: Dispatches parallel coder agents for each task in a wave and gates results with a code-review step before moving to the next wave.
  • Spec-driven workflows: Reads a specs/{feature}/ folder containing README.md, requirements.md, and task-*.md files to guide work.
  • Resumable progress & governance: Picks up exactly where it left off and tracks task statuses across waves, with built-in review loops.

Quick Start

Provide a specs/{feature} folder and run the orchestrator to begin the feature's wave-by-wave implementation.

Frequently Asked Questions about implement-feature

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

FAQPage Schema
How do I orchestrate parallel coding agents for feature implementation?

Parallel coding agent orchestration dispatches coder agents wave-by-wave, using code review gates between waves to ensure quality before advancing to subsequent tasks.

What is a spec-driven workflow for parallel feature builds?

A spec-driven workflow reads a specs/{feature}/ folder containing README.md, requirements.md, and task files to provide context and guide parallel coder agents through implementation.

How do I resume a parallel feature build after stopping midway?

Resuming a parallel feature build works by picking up exactly where the orchestrator left off, tracking task statuses across waves in the spec files to continue execution seamlessly.

Can I run feature implementation tasks in parallel without manual code review gates?

Feature implementation requires a single code-review gate after each wave of parallel tasks, ensuring quality control before advancing to the next set of dispatched coder agents.

Does the orchestrator write code directly during spec implementation?

The orchestrator never writes code itself during spec implementation; it only provides task context, collects results, handles fix loops, and records progress in the spec files.

What file structure is needed to start a wave-based feature implementation?

Wave-based feature implementation requires a specs/{feature}/ folder containing README.md, requirements.md, and task-*.md files to define the work for the coder agents.