methodology

Automates AI-first development workflows from specification to deployment.

12|2|Updated Feb 2, 2020
One-click install
npx skills add https://github.com/servitola/dotfiles --skill methodology-servitola
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: methodology
Source: https://github.com/servitola/dotfiles/tree/main/claude-code/skills/methodology
Command: npx skills add https://github.com/servitola/dotfiles --skill methodology-servitola

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI-driven project work suffers from scattered documentation, inconsistent specs, and governance gaps across teams. The methodology provides a structured, end-to-end pipeline with validators, clear roles, and centralized project knowledge to keep work aligned from idea to deployment.

Core Features & Use Cases

  • Spec-driven pipeline: translate ideas into user specs, tech specs, and task decomposition.
  • Validators and governance: automated checks at each stage to catch defects early.
  • Knowledge management: centralizes project knowledge and ensures PK stays up to date.

Quick Start

Read the pipeline guide in references/pipeline.md to begin applying the methodology to your project.

Frequently Asked Questions about methodology

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

FAQPage Schema
What is an AI-first development workflow and how does it manage project specifications?

An AI-first development workflow automates project progression from specification to deployment using a structured pipeline. It translates ideas into user specs, tech specs, and task decomposition while enforcing governance through automated validators at each stage.

How do I standardize AI project governance and maintain consistent project knowledge across teams?

Standardize AI project governance by applying a structured pipeline with automated validators at each stage. Centralize project knowledge using a YAML frontmatter metadata model to keep documentation aligned and current from idea to deployment.

How do I set up a spec-driven pipeline for AI-driven project work?

Set up a spec-driven pipeline by reading the pipeline guide in references/pipeline.md. This initiates the methodology, applying validators and a YAML frontmatter metadata model to translate ideas into structured specs and task decomposition.

Does this methodology require any specific dependencies or frameworks to start managing AI pipelines?

No specific dependencies are required to start managing AI pipelines. The methodology provides a self-contained workflow that uses YAML frontmatter for metadata modeling and reference files for pipeline guidance.

What's the best way to decompose tasks and ensure QA alignment in AI-first development?

The best way to decompose tasks and ensure QA alignment is using a structured development pipeline. It applies automated validators during implementation and QA stages to catch defects early and maintain alignment with project-knowledge standards.

When should I not use a structured AI governance pipeline for my software project?

Avoid a structured AI governance pipeline for small, informal projects where scattered documentation poses minimal risk. The overhead of YAML metadata modeling and stage validators is designed for scalable, team-based development needing strict alignment.