project-init

Create standardized AI-execution project scaffolds with CLAUDE.md, Diátaxis docs, and datarim workflow directories.

11|1|Updated Apr 10, 2026

Search Tags:#AI workflow #CLAUDE.md #project scaffolding #tech stack selection #documentation taxonomy #idempotent initialization

Ready to run

npx skills add https://github.com/Arcanada-one/datarim --skill project-init-arcanada-one

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: project-init
Source: https://github.com/Arcanada-one/datarim/tree/main/skills/project-init
Command: npx skills add https://github.com/Arcanada-one/datarim --skill project-init-arcanada-one

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of starting new projects with inconsistent structure, missing workflow state, and poor repeatability across AI-assisted executions.

Core Features & Use Cases

Standardized project scaffolding: creates CLAUDE.md, a Diátaxis documentation tree, and a datarim workflow state folder.
Tech-stack-aware setup: generates a stack-appropriate .gitignore and fills CLAUDE.md build/config placeholders from stack selection.
Idempotent updates: never overwrites existing files, only creates missing directories/files and reports what was skipped.

Quick Start

Tell your AI assistant: /dr-init create project "MyProject" with a one-line description and project type, and it will scaffold the full project structure in your target folder.

Frequently Asked Questions about project-init

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

FAQPage Schema

How do I scaffold an AI-ready project structure with CLAUDE.md?▼

To scaffold an AI-ready project, this skill generates CLAUDE.md, a Diátaxis documentation tree, and datarim workflow state directories. It conditionally fills build placeholders using a separate tech-stack selection document to ensure consistent AI-assisted execution.

What is idempotent project scaffolding and why does it matter for AI workflows?▼

Idempotent project scaffolding initializes a project structure without overwriting existing files. It only creates missing directories and reports skipped files, allowing safe incremental re-scaffolding when project intent signals change during AI-assisted workflows.

How do I set up a Diátaxis documentation taxonomy for a new software project?▼

Setting up a Diátaxis documentation taxonomy is handled by generating a standardized documentation tree during project initialization. This creates a structured layout for tutorials, how-to guides, references, and explanations tailored for AI execution.

Can I re-scaffold an existing project without losing my current configuration files?▼

Yes, you can re-scaffold an existing project without losing files because initialization operations are idempotent. The process detects project intent signals via triggers, only creates missing directories or files, and explicitly reports what was skipped.

Does project initialization automatically generate a .gitignore based on my selected tech stack?▼

Yes, project initialization generates a stack-appropriate .gitignore. It reads your tech stack configuration from a separate decision document and fills the CLAUDE.md build and config placeholders accordingly to match your stack.

Why do I need workflow state directories for AI-assisted development?▼

Workflow state directories are needed to maintain consistent execution context across AI-assisted development sessions. They store datarim workflow states, preventing repeatability issues and missing state tracking when starting new projects.