How does it identify my project's tech stack?

The skill performs a deep scan of configuration files (like package.json or pyproject.toml), entry points, and environment markers to determine languages, frameworks, and tools.

What is the benefit of the .rune/ directory?

The .rune/ directory acts as a persistent memory layer for the AI, storing architectural decisions, learned instincts, and project-specific conventions that standard READMEs often omit.

What files does the onboard skill create?

It generates a CLAUDE.md file in the project root and a .rune/ directory containing conventions.md, decisions.md, progress.md, and a human-readable DEVELOPER-GUIDE.md.

Does it overwrite my existing documentation?

No. It intelligently merges findings into existing CLAUDE.md files while preserving manual comments, and it skips existing developer guides to protect manual content.

Project Onboarder

Name: Project Onboarder
Author: Rune-kit

byRune-kit

•

Aprendizaje y Documentación

Automatically generates comprehensive project context and documentation to jumpstart AI-assisted development sessions.

The onboard skill eliminates the manual setup overhead by scanning your codebase to detect tech stacks, naming conventions, and architectural patterns. It generates a standardized CLAUDE.md configuration and a specialized .rune/ state directory, ensuring every future AI session starts with deep project intelligence. By automating context gathering and environment validation, it saves developers significant time typically spent re-explaining project structures, while also producing human-readable onboarding guides for new team members.

Características Principales

01Context budget auditing to optimize AI performance

0257 GitHub stars

03Coding convention extraction for style-consistent AI generation

04Automated tech stack, framework, and dependency detection

05Generation of CLAUDE.md and .rune/ state management files

06Human-readable DEVELOPER-GUIDE.md generation

Casos de Uso

01Bridging project state and architectural decisions across multiple AI sessions

02Standardizing project documentation and AI instructions across team repositories

03Initializing AI-ready context for legacy or undocumented codebases

Características Principales

01Context budget auditing to optimize AI performance

0257 GitHub stars

03Coding convention extraction for style-consistent AI generation

04Automated tech stack, framework, and dependency detection

05Generation of CLAUDE.md and .rune/ state management files

06Human-readable DEVELOPER-GUIDE.md generation

Casos de Uso

01Bridging project state and architectural decisions across multiple AI sessions

02Standardizing project documentation and AI instructions across team repositories

03Initializing AI-ready context for legacy or undocumented codebases