writing-plans

Generate structured implementation plans with tasks, context, and verification steps.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/kirvin/copilot-cli-essentials --skill writing-plans-kirvin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/kirvin/copilot-cli-essentials/tree/main/plugins/cpe/skills/writing-plans
Command: npx skills add https://github.com/kirvin/copilot-cli-essentials --skill writing-plans-kirvin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps users create detailed, step-by-step implementation plans for agentic execution, ensuring clarity, task definition, and efficient workflow design.

Core Features & Use Cases

  • Structured Plan Creation: Generates plans with clear sections for problem, goal, scope, and tasks.
  • Task Definition: Ensures each task is a complete unit of work for a single agent.
  • Parallelization Guidance: Helps structure plans for parallel execution across subsystems.
  • Use Case: A developer needs to implement a new feature. They use this Skill to draft a plan that breaks down the work into manageable, executable tasks for an AI agent, including context loading and verification steps.

Quick Start

Use the writing-plans skill to create a new implementation plan for the feature 'user authentication'.

Frequently Asked Questions about writing-plans

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

FAQPage Schema
What is an implementation plan for agentic execution?

It defines explicit path definitions, context per task, and verification steps, ensuring each task acts as a complete unit of work for a single agent to execute accurately.

How do I create a structured implementation plan for AI-driven development?

The plan structures each task as a complete unit of work for a single agent, facilitating parallelization and context loading for efficient AI-driven development workflows.

Can I parallelize tasks across subsystems in my workflow design?

This parallelization guidance ensures efficient agentic execution by treating each task as an independent unit with its own context and verification steps.

Do I need to define context and verification steps for each task?

These requirements guarantee that every granular task functions as a complete unit of work for a single agent, minimizing errors in AI-driven workflows.

What's the best way to break down a software feature into manageable tasks?

This approach ensures clarity and task definition, allowing a single agent to handle each complete unit of work efficiently within the overall implementation plan.