project-seeding

Generates project plans and documentation from a goal via a two-step process.

1|Updated Apr 21, 2026
One-click install
npx skills add https://github.com/sannidhyas/howl-pa --skill project-seeding
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: project-seeding
Source: https://github.com/sannidhyas/howl-pa/tree/main/claude-plugin/skills/project-seeding
Command: npx skills add https://github.com/sannidhyas/howl-pa --skill project-seeding

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of creating a comprehensive project plan from a goal, ensuring that all necessary components and considerations are accounted for before starting work.

Core Features & Use Cases

  • Two-Pass Methodology: Forward pass to establish true facts and backward pass to decompose the goal into actionable tasks.
  • Documentation Generation: Produces FOUNDATIONS.md, LANDSCAPE.md, PLAN.md, and RECONCILIATION.md for a thorough project plan.
  • Use Case: When initiating a new project or significant work on an existing codebase, this Skill helps in structuring the project plan and architecture.

Quick Start

To seed a new project, run the 'project-seeding' skill and follow the prompts to input your project goal and relevant details.

Frequently Asked Questions about project-seeding

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

FAQPage Schema
How do I structure a project plan from a high-level goal using first-principles?

First-principles project planning structures a goal by establishing true facts in a forward pass, then decomposing the goal backward into actionable tasks. This generates foundational documents to ensure all necessary components are accounted for before development.

How does a two-pass methodology work for codebase analysis and project architecture?

The two-pass methodology works by first generating a forward pass to establish true facts and foundational documents, then executing a backward pass to decompose goals into plans and reconcile them with the project architecture.

What's the best way to generate documentation for greenfield and brownfield project planning?

Generate comprehensive project planning documentation by running a structured seeding process that produces FOUNDATIONS.md, LANDSCAPE.md, PLAN.md, and RECONCILIATION.md, suitable for both greenfield and existing brownfield codebases.

Can I use this project architecture approach for an existing codebase?

Yes, the project seeding methodology is suitable for brownfield projects with an existing codebase as well as greenfield initiatives. It requires human review and iterative planning to reconcile new plans with existing foundations.

What documents are needed to decompose project goals into actionable tasks?

To decompose project goals into actionable tasks, you need foundational and landscape documents to establish facts, followed by a plan document and a reconciliation document to align the decomposed tasks with the project architecture.

When should I not use an automated project architecture seeding approach?

You should not rely solely on automated project seeding without human review. The methodology requires iterative planning and human oversight to validate the generated architectural foundations and reconciled plans against real-world constraints.