implement-feature

Coordinate parallel coder agents across waves with code-review gates and final lint/typecheck integration checks.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/arka6fx/pixify --skill implement-feature-arka6fx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: implement-feature
Source: https://github.com/arka6fx/pixify/tree/main/.agents/skills/implement-feature
Command: npx skills add https://github.com/arka6fx/pixify --skill implement-feature-arka6fx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill coordinates a team of coder agents to implement a feature specification by breaking work into waves, dispatching tasks in parallel, and gating with code reviews between waves. It does not write code itself but orchestrates the work and ensures smooth handoffs between waves.

Core Features & Use Cases

  • Wave-based orchestration: loads a specs/{feature}/ folder, identifies the next incomplete wave, and prepares the tasks for parallel execution.
  • Parallel coder agents: spawns coder subagents for each task with focused context, enabling concurrent progress.
  • Code review gate: runs a unified review step between waves to verify integration, quality, and safety.
  • Resumable progress tracking: can resume from the exact point it left off by reading the spec task statuses.
  • Non-code-writing orchestrator: the orchestrator manages coordination and commits only after successful review.

Quick Start

Create a specs/{feature}/ folder with task-{nn}-*.md files, then invoke the skill to start implementing the feature.

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 coder agents to implement a feature specification?

You orchestrate parallel coder agents by loading a specs/{feature}/ folder, identifying incomplete waves, and dispatching tasks concurrently. A code review gate runs between waves to verify integration, quality, and safety before proceeding.

Can I resume feature implementation from the exact point a previous parallel workflow stopped?

Yes, you can resume feature implementation by reading spec task statuses. The orchestrator tracks progress in spec files, allowing it to restart from the exact incomplete wave and task it left off without losing prior context.

How do code review gates work between parallel coding workflows?

Code review gates between parallel coding workflows run a unified review step after each wave completes. This verifies integration, quality, and safety, ensuring the orchestrator only commits code after successful review and final lint and typecheck passes.

What is the best way to break down a feature specification into parallel tasks?

The best way to break down a feature specification is using a wave-based structure with task-{nn}-*.md files in a specs/{feature}/ folder. The orchestrator executes these tasks concurrently across waves, gating progress with code reviews.

Does the feature implementation orchestrator write code itself?

No, the feature implementation orchestrator does not write code itself. It enforces non-code-writing orchestration by managing coordination, spawning coder subagents for parallel execution, and committing only after successful reviews.

What final integration checks are enforced before committing parallel coded features?

Final integration checks enforced before committing parallel coded features include running lint and typecheck processes. The orchestrator ensures these checks pass alongside the unified code review gate before any code is committed.