lunar-claude

Operational tooling for Talos Linux Kubernetes clusters via Sidero Omni with Proxmox infrastructure provider, covering machine classes, CEL storage selectors, and provider lifecycle management.

Mise configuration patterns, task definitions, hooks, presets, and language-specific setup guidance for dev environment management and project tooling.

Files a GitHub issue on this repo to tell Brent about anything worth his attention — confusion, something that didn't work, an idea or wish, or a new way the user phrased a request. Brent is a collaborator on this private repo and uses these issues to fix and improve the tools. Use this whenever the user sounds confused or frustrated, says something is broken or didn't work as expected, wishes something worked differently, or asks to tell Brent something — even if they never say "feedback" or "issue". Also invoked by blake-os:git-ops to log a request it could not cleanly route.

Internal commit step for the blake-os git-ops router. Stages explicit file paths and creates atomic commits on the current branch, matching the repo's existing message style and scanning for secrets before staging. Invoked by blake-os:git-ops — not a direct entry point. Trigger directly only on the exact request "git commit".

Single front door for everything git and GitHub — saving work, getting the latest, backing up, and putting changes online. Routes plain-language requests to the right operation in the correct order, even when the user does not use git terms. Use whenever the user wants to save, back up, update, sync, upload, publish, or check on their project's files — phrases like "save my work", "back it up", "I'm done", "get the latest", "put it online", "did it save?".

Internal push step for the blake-os git-ops router. Publishes local commits to origin only when the branch is current, after verifying it is not behind; never force-pushes. Invoked by blake-os:git-ops — not a direct entry point. Trigger directly only on the exact request "git push".

Internal sync step for the blake-os git-ops router. Brings the current branch up to date with origin — fast-forwards when only behind, makes a merge commit when local and remote diverged, aborts and hands off on conflict; never rebases or force-pushes. Invoked by blake-os:git-ops — not a direct entry point. Trigger directly only on the exact request "git pull" or "git sync".

Structured root cause analysis for macOS failures. Scaffold stub — replace with the authored skill.

Summarize the current state of the git repository

Best practices for git workflow automation including atomic commits, branch naming, conventional commit format, and changelog generation.

Run hooks and create clean, logical commits via the commit-craft agent.

Guidance for creating effective Claude Code plugin skills with proper structure, progressive disclosure, and content organization best practices.

Knowledge and guardrails for the mise + fnox + infisical secrets toolchain, covering secret injection, secret providers, and env var hygiene.

Release conventions and changelog configuration for lunar-claude, covering version bumping, changelog generation via git-cliff, and release tagging.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.

Guide for creating effective skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Process video files with audio extraction, format conversion (mp4, webm), and Whisper transcription.

Builds production-ready applications with the Claude Agent SDK for Python, covering orchestrators with subagents, programmatic agent configuration, hooks, and permissions.

Python JSON parsing best practices covering performance optimization (orjson/msgspec), handling large files (streaming/JSONL), security (injection prevention), and advanced querying (JSONPath/JMESPath).

Python single-file script development using uv and PEP 723 inline metadata, preventing invalid patterns like [tool.uv.metadata].

Structured frameworks for documenting architectural decisions using MADR templates, option analysis, trade-off matrices, and human-in-the-loop AI assistance.

Implements robust error handling in Ansible using block/rescue/always patterns, retry logic with until/retries, and clear assertion patterns for graceful failure management.

Core principles and golden rules for writing production-quality Ansible automation, covering FQCN requirements, module selection guidance, and execution patterns using uv run.

Techniques for writing truly idempotent Ansible tasks using changed_when, failed_when, and check-before-create patterns to eliminate spurious "changed" reports.

Patterns for designing well-structured, maintainable Ansible playbooks with state-based (present/absent) design, play organization, and proper variable scoping.

Expert Proxmox VE automation using the community.proxmox Ansible collection for VM provisioning, template management, and cluster operations with minimal CLI usage.

Production-grade Ansible role structure patterns for directory layout, variable organization (defaults vs vars), handlers, and task organization, derived from analysis of 7 geerlingguy production roles.

Secure secrets handling in Ansible with Infisical vault integration, no_log directive enforcement, and a reusable Infisical lookup task for safe credential retrieval.

Testing strategies and ansible-lint configuration for validating Ansible automation quality, covering lint rules, syntax validation, and integration test setup.

Manage the Matrix/Virgo-Core Proxmox VE cluster (nodes Foxtrot, Golf, Hotel - MINISFORUM MS-A2 with AMD Ryzen 9 9955HX). Covers VM provisioning, VLAN networking, CEPH storage, and automation via Python (proxmoxer), Ansible (community.general.proxmox), and Terraform (Telmate/proxmox).

AI-powered code review using CodeRabbit CLI and GitHub integration, covering local reviews, .coderabbit.yaml configuration, and automated review pipelines.

Guidance for writing Hookify rules — markdown files with YAML frontmatter that define behavioral patterns and conversation automation hooks.

Decision frameworks and patterns for choosing and composing Claude Code components — skills, sub-agents, hooks, MCP servers, and slash commands — into effective multi-component agentic systems with proper orchestration and context management.

Research-backed skill creation workflow with automated firecrawl research gathering, multi-tier validation, and comprehensive auditing across a 9-phase process from research through final audit, following Anthropic specifications for Claude Code.

Guidance for developing Claude Code sub-agents with proper frontmatter, system prompts, triggering conditions, and autonomous task handling patterns.

Guidance for creating Claude Code slash commands with YAML frontmatter, dynamic arguments, bash execution, and user interaction patterns.

Comprehensive guidance for creating Claude Code plugin hooks — event-driven automation using PreToolUse, PostToolUse, Stop, and other lifecycle events via the advanced prompt-based hooks API.

Guidance for integrating Model Context Protocol (MCP) servers into Claude Code plugins, supporting SSE, stdio, HTTP, and WebSocket server types for external service connectivity.

Documents the .claude/plugin-name.local.md pattern for storing user-configurable plugin settings and state using YAML frontmatter and markdown content.

Guidance for Claude Code plugin directory structure, plugin.json manifest configuration, component auto-discovery, and file naming conventions.