onboard

Load CBass project context, architecture, and service inventory into a fresh Claude session.

2|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/mdc159/cbass --skill onboard-mdc159
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: onboard
Source: https://github.com/mdc159/cbass/tree/main/.claude/skills/onboard-v1.0.0
Command: npx skills add https://github.com/mdc159/cbass --skill onboard-mdc159

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Starting work on the CBass self-hosted AI stack without context forces repeated re-reading of documentation and leads to mistakes like using localhost instead of Docker container names or misconfiguring GPU profiles and environment modes. ## Core Features & Use Cases - Project Context Loading: Provides architecture overview, service inventory, key files, and current project state for the CBass Docker Compose stack. - Focus-Area Onboarding: Supports targeted context for n8n workflows, Flowise chatflows, deployment operations, and the data layer (Supabase, Qdrant, Neo4j). - Use Case: A developer returning to the project after a break invokes the skill with the n8n focus to immediately get webhook integration details, credential configuration rules, and pre-built workflow locations before editing automations. ## Quick Start Ask the agent to onboard onto the CBass project with a focus on n8n before modifying any workflows.

Frequently Asked Questions about onboard

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

FAQPage Schema
How do I onboard an AI agent onto an existing Docker Compose project?

Invoke the onboard skill to load project context including architecture, service inventory, and key files. Optionally specify a focus area such as n8n, flowise, deploy, or data to narrow the loaded documentation.

What focus areas does the CBass onboard skill support?

The skill supports four focus areas: n8n for workflow automation, flowise for chatflows and agents, deploy for VPS and local deployment, and data for Supabase, Qdrant, and Neo4j. Running it without arguments loads full project context.

How do services communicate inside the CBass Docker network?

Services communicate over the localai_default Docker network using container names instead of localhost. Examples include http://ollama:11434 for Ollama, http://qdrant:6333 for Qdrant, and postgresql://db:5432 for Supabase PostgreSQL.

Can I use the onboard skill for deployment tasks on the VPS?

Yes, the deploy focus area loads VPS setup, local development, and DNS/SSL documentation. It covers GPU profiles like gpu-nvidia and cpu, plus environment modes private and public used by start_services.py.

What are the limitations of the onboard skill?

The skill only reads and summarizes existing project documentation; it does not modify files, run Docker commands, or verify live service status. Current todo items and known issues must be checked separately in CLAUDE.md.