deep-plan

Generate structured implementation plans from vague feature requests.

Updated Feb 28, 2026
One-click install
npx skills add https://github.com/b4r7x/agent-skills --skill deep-plan-b4r7x
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-plan
Source: https://github.com/b4r7x/agent-skills/tree/main/deep-plan
Command: npx skills add https://github.com/b4r7x/agent-skills --skill deep-plan-b4r7x

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill transforms vague ideas into actionable, structured implementation plans by deeply researching the project context, asking clarifying questions, and generating a precise internal prompt for execution.

Core Features & Use Cases

  • Deep Project Research: Analyzes existing code, documentation, and git history to understand the project's context.
  • Clarifying Questions: Interactively asks the user targeted questions to resolve ambiguities.
  • Structured Plan Generation: Produces a detailed plan including problem statement, approach, file changes, todos, and considerations.
  • Use Case: You have a new feature request like "add dark mode to the app". This Skill will research your current theming, ask if you want to persist preferences, and then generate a plan detailing which files to modify, what code to add, and the steps to implement it.

Quick Start

Use the deep-plan skill to create a plan for adding a user profile page.

Frequently Asked Questions about deep-plan

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

FAQPage Schema
How do I generate an implementation plan for a vague feature request?

To generate an implementation plan for a vague feature request, you can use an AI assistant to research project context, ask clarifying questions, and decompose the idea into a structured plan with actionable todos.

How does AI project management handle unpolished prompt ideas?

AI project management handles unpolished prompt ideas by performing deep dives into existing project files and git history, interactively asking targeted questions, and then generating a detailed internal prompt for execution.

What is the best way to structure feature development todos from a rough idea?

The best way to structure feature development todos from a rough idea is to autonomously analyze current code and documentation, resolve ambiguities through clarifying questions, and output a structured plan detailing file changes and steps.

Can I save generated implementation plans to a markdown file?

Yes, you can save generated implementation plans to a markdown file by using plan mode, which automatically saves the structured output to plan.md and can populate SQL todos for tracking.

Does deep project research help with code generation for new features?

Yes, deep project research helps with code generation by analyzing your existing code, documentation, and git history to understand the project context before producing a precise internal prompt for execution.