jmagar/lab

Agent Client Protocol skills for Rust, Python, and TypeScript implementations.

AdGuard Home DNS-level ad blocking and network filtering via direct calls to the AdGuard Home control API.

Browser automation plugin for agent-driven web app testing, inspection, and debugging.

Drive the agent-os Windows 11 sandbox VM through its Windows-MCP server — desktop automation, Windows app testing, screenshots, shell commands, and VM health checks.

Development kit for working with the Claude Agent SDK

Send push notifications via apprise-mcp — a Rust MCP bridge to the Apprise universal notification library.

The *arr / media-automation stack — Radarr, Sonarr, Prowlarr, Overseerr, SABnzbd, qBittorrent, Plex, Jellyfin, Tautulli, and Tracearr — each via its own REST API.

Skills and MCP configuration for the Axon crawl, ingest, embed, query, and RAG engine.

AI-supervised issue tracker for coding workflows

Bitwarden and secrets-management workflows for homelab operations.

Skills for operating a ByteStash snippet manager.

Control and inspect a live Chrome browser from your coding agent. Record performance traces, analyze network requests, check console messages with source-mapped stack traces, and automate browser actions with Puppeteer.

Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.

Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives

Agent that simplifies and refines code for clarity, consistency, and maintainability while preserving functionality. Focuses on recently modified code.

OpenAI Codex plugin for Claude Code interoperability.

Multi-perspective code analysis covering architecture, security, and best practices

Homelab syslog receiver plus MCP server for searching, tailing, and correlating logs across hosts.

Discord messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /discord:access.

Real-time Docker container log viewer via the direct Dozzle API and native Dozzle MCP server.

Localhost web chat for testing the channel notification flow. No tokens, no access control, no third-party service.

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics.

Go language server for code intelligence and refactoring

Gotify push notification server via the rustify MCP server.

Self-hosted photo and video management via direct calls to the Immich REST API.

Kotlin language server for code intelligence

Skills and MCP configuration for the Lab homelab control plane.

30 specialized agents, 28 commands, 15 skills, persistent memory with auto-recall

Skills for operating a Linkding bookmark manager.

Docker container log alerting via keyword/regex patterns, configured through LoggiFly's config.yaml.

Precise local semantic code search via MCP. Indexes your codebase with Go AST parsing and vector embeddings — Ollama, LM Studio, or HuggingFace TEI.

Claude Code skill for building MCP Apps with interactive UIs

Skills for designing and building MCP servers that work seamlessly with Claude. Guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and interactive MCP apps.

Connect Claude to a private MCP server through an Anthropic-managed tunnel.

Skills for operating a Memos note hub.

Self-hosted Navidrome music server via its Subsonic API with direct HTTP calls.

Graph database Cypher queries and schema inspection via Neo4j's HTTP transactional Cypher API.

NotebookLM research, source, generation, and download workflows.

NVIDIA agent skills for accelerated-computing workflows — starting with cuOpt vehicle-routing optimization (VRP, TSP, PDP) via the cuOpt Python API.

Creates interactive HTML playgrounds — self-contained single-file explorers with visual controls, live preview, and prompt output with copy button. Includes templates for design playgrounds, data explorers, concept maps, and document critique.

Remote-device memory and live operating context for host-specific work — a CLAUDE.md-style memory file per host combined with live SSH, Tailscale, Docker, systemd, and log context.

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

Python language server (Pyright) for type checking and code intelligence

Vector database collections and semantic search via direct calls to the Qdrant REST API.

Agent skills for Qdrant vector search covering scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage.

CalDAV and CardDAV workflow skills for Radicale.

Interactive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until completion.

Arcane Docker management via the rarcane MCP server (Rust port of arcane-mcp).

Redis development best practices — data structures, query engine, vector search, caching, and performance optimization

Reference rmcp template/example MCP server — scaffold for building new Rust MCP servers.

Rust language server for code intelligence and analysis

SMART hard-drive health monitoring via direct calls to the Scrutiny web API.

Semantic code analysis MCP server providing intelligent code understanding, refactoring suggestions, and codebase navigation through language server protocol integration.

Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.

Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.

Core skills library: TDD, debugging, collaboration patterns, and proven techniques

SWAG reverse proxy configuration management via MCP. Create, edit, view, and manage nginx proxy configurations with auth integration.

Tailscale network management via the rustscale MCP server — query devices, ACL, DNS, users, and API keys.

HuggingFace Text Embeddings Inference (embed, rerank, tokenize) via direct calls to the TEI HTTP API.

Telegram messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /telegram:access.

App-testing and MCP-tooling skills: live web/Android/desktop app QA, MCP server smoke-testing (mcporter), MCP-UI validation (mcpjam), and claude-in-mobile device automation.

TypeScript/JavaScript language server for enhanced code intelligence

UniFi network management via the rustifi MCP server — monitor devices, clients, health, alarms, events, and WLANs.

UniFi Network MCP server (sirkirby/unifi-mcp) — manage network devices, clients, firewall, VPN, and more.

Unraid NAS/homelab monitoring via the unrust MCP server.

Read-only Uptime Kuma monitoring via direct HTTP (Prometheus /metrics + status-page JSON).

Session, repo status, GitHub review, and CI workflow skills for branch/worktree readiness audits, quick push, session documentation, PR comments, and CI debugging.

Turn your coding agent into a browser agent using a local Playwright workspace, screenshots, action logs, and visual self-verification.

Download audio/video from any yt-dlp-supported site, embed metadata and cover art, organize by artist, and rsync to an SSH remote with separate audio/video destinations.

Zsh shell for Claude Code - full terminal control, live output, PTY mode for interactive commands