create-plan

Create executable implementation plans with phases, tasks, and ADRs.

17|1|Updated Dec 7, 2025
One-click install
npx skills add https://github.com/mhylle/claude-skills-collection --skill create-plan-mhylle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-plan
Source: https://github.com/mhylle/claude-skills-collection/tree/main/skills/create-plan
Command: npx skills add https://github.com/mhylle/claude-skills-collection --skill create-plan-mhylle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams transform vague feature ideas into structured, executable implementation plans through guided research, multi-phase design, and explicit verification.

Core Features & Use Cases

  • Research-led planning: break down user stories into actionable phases with assigned tasks and dependencies.
  • ADR-aware design: capture architectural decisions and rationale to ensure future clarity.
  • Progress-driven planning: generate tasks, document progress, and enable multi-session collaboration.

Quick Start

Start by creating a new plan file and specify the feature name and goals. Then define phases, verification criteria, and tasks according to the workflow described.

Frequently Asked Questions about create-plan

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

FAQPage Schema
How do I create an executable implementation plan for a new feature?

To create an executable implementation plan, use structured research and multi-phase design to break down feature goals into assigned tasks, explicit phases, and verification criteria. This transforms vague ideas into actionable work through guided, collaborative task-tracking.

What is the best way to document architectural decisions during technical planning?

The best way to document architectural decisions during technical planning is by using Architecture Decision Records (ADR). Capturing design decisions and their rationale ensures future clarity and provides context for complex refactors across multiple sessions.

How does research-led planning work for complex software refactors?

Research-led planning for complex refactors works by guiding users from the initial task description through multi-phase design. It enforces explicit research tasks, captures context, and generates task-based progress tracking to ensure structured, verifiable implementation.

Can I track task progress across multiple sessions for a design doc?

Yes, you can track task progress across multiple sessions. The skill generates tasks, documents progress, and enables multi-session collaboration by maintaining a structured plan file with explicit phases and verification criteria.

Does structured planning help break down user stories into actionable phases?

Structured planning helps break down user stories into actionable phases by assigning dependencies and verification criteria. It transforms feature descriptions into a multi-phase design with explicit tasks and ADR-aware documentation.