homelab-core

View the latest screenshot from ~/Pictures/Screenshots

Deploy all MCP plugin servers from .claude-plugin/marketplace.json

Analyze disk space usage across all mounts

Check health of all Docker containers and services

Check CPU, RAM, temps, and system load

Use this agent when you need AI-powered deep research and analysis via Google NotebookLM. <example> Context: Orchestrator has spawned this agent for NotebookLM analysis phase user: "You are the NotebookLM specialist. Research brief: [topic]. Notebook ID: abc123. Output: ./docs/research/..." assistant: "Reading my skills and starting NotebookLM deep research immediately (15-30 min operation)." <commentary> This agent is spawned by the orchestrator with a pre-created notebook ID. It immediately starts deep research (longest operation), then adds sources as they're relayed by the orchestrator, conducts Q&A, and generates artifacts. </commentary> </example> <example> Context: Orchestrator relays high-quality URLs to add as sources user: "Add these 5 sources to the notebook: [URLs with descriptions and quality tiers]" assistant: "Adding sources to notebook abc123 using -n flag for parallel safety." <commentary> The specialist receives batched URL recommendations from the orchestrator throughout the research process, prioritizing higher-tier sources to stay within the 300-source limit. </commentary> </example>

Manage code snippets in ByteStash snippet storage service. This skill should be used when the user asks to "save a snippet", "search snippets", "find code", "share snippet", "organize snippets", "list my snippets", "create snippet", "delete snippet", or mentions ByteStash, code storage, snippet management, or code archival.

This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches comments via gh CLI, creates task checklists, links commits to review threads, and blocks completion if unresolved threads remain.

Unified health dashboard for all configured homelab services. Use when the user wants to check service status, verify credentials work, see which services are reachable, or diagnose connectivity issues. Triggers on: 'check health', 'service status', 'what's running', 'is plex up', 'verify my setup', 'homelab health', or after running /homelab-core:setup.

Interactive credential setup wizard for claude-homelab. Use when the user wants to configure credentials, set up a new service, update API keys, or run initial setup after installing the homelab-core plugin. Triggers on: 'setup credentials', 'configure plex', 'add my API key', 'I just installed homelab-core', 'setup homelab', or any mention of needing to configure a specific service.

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.