feature-custom-dev

Organize complex feature development into a phased, plan-driven workflow.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/mataanin/multi-llm --skill feature-custom-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: feature-custom-dev
Source: https://github.com/mataanin/multi-llm/tree/main/skills/feature-custom-dev
Command: npx skills add https://github.com/mataanin/multi-llm --skill feature-custom-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured, plan-driven workflow to guide developers through discovery, architecture design, and validation for new features, reducing ambiguity and rework.

Core Features & Use Cases

  • Phased workflow: Discovery, clarifying questions, architecture design, and plan review with AI-assisted insights.
  • Plan-mode governance: Exits plan mode to produce a durable execution plan and artifacts (docs/plans).
  • Multi-model collaboration: Leverages Claude and external LLMs for exploration and architecture, then consolidates results into a cohesive plan.
  • QA & validation scaffolds: Integrates QA planning, review cycles, and production validation sections in the plan.

Quick Start

Outline the feature, review the codebase, and confirm requirements before drafting the architecture plan.

Frequently Asked Questions about feature-custom-dev

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

FAQPage Schema
How do I plan feature development across a complex codebase?

Feature development planning requires a phased workflow that handles discovery, clarifying questions, architecture design, and risk-checked plan reviews to reduce ambiguity and rework across complex codebases.

What is plan mode governance for architecture design?

Plan mode governance orchestrates discovery and architecture design phases, then exits plan mode to produce durable execution artifacts like architecture docs, QA plans, and production validation sections for software teams.

How do I structure a feature development workflow with AI collaboration?

AI collaboration for feature development leverages Claude and external LLMs to explore codebases and design architecture, then consolidates multi-model results into a cohesive, risk-checked execution plan with integrated QA scaffolds.

Can I integrate QA planning and production validation into my architecture plan?

QA planning and production validation integrate directly into the architecture plan through dedicated scaffolds, supporting review cycles and validation sections that ensure feature durability before execution begins.

What's the best way to reduce ambiguity and rework when building new features?

Reducing ambiguity and rework requires a structured, plan-driven workflow that enforces phased discovery and clarifying questions before architecture design, ensuring requirements are confirmed before drafting execution plans.

Are there prerequisites for using a plan-driven feature development workflow?

Plan-driven feature development requires an existing codebase to review and a defined feature outline. Developers must confirm requirements and review the codebase before the workflow can draft architecture plans.