ExcellentMaps

Lunacy Studio Skills — Security skill for Claude Code

Security community

A seven-skill security toolkit for Claude Code that audits any web project, finds the holes, and closes them — in plain language, without breaking what works.

How to install Lunacy Studio Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ExcellentMaps/lunacy-studio-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Lunacy Studio Skills does

A seven-skill security toolkit for Claude Code that audits any web project, finds the holes, and closes them — in plain language, without breaking what works.

Alternatives in Security

Security Best Practices — Review code for language-specific security vulnerabilities 14.6k ★
Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
Mcp-scan (Invariant Labs) — MCP security scanner with proxy mode for real-time scanning without infrastructure changes 1.9k ★

README

Guard Security Suite

**A seven-skill security toolkit for Claude Code that audits any web project, finds the holes, and closes them — in plain language, without breaking what works.**

[![License: CC BY-ND 4.0](https://img.shields.io/badge/License-CC%20BY--ND%204.0-lightgrey.svg)](LICENSE) [![Author: ExcellentMaps](https://img.shields.io/badge/Author-ExcellentMaps-blue.svg)](https://github.com/ExcellentMaps) [![Skills: 7](https://img.shields.io/badge/Skills-7-green.svg)](#the-seven-skills)

[Русская версия →](README.ru.md)

What this is

Guard Security Suite is a set of [Agent Skills](https://docs.claude.com/en/docs/agents-and-tools/agent-skills) for Claude Code. Install it once, then ask in plain words — *"audit my project"*, *"what's not protected?"*, *"protect my CRM"* — and Claude runs a structured security review, explains every finding in language a non-engineer understands, and implements the fixes one at a time with a verification and a rollback for each.

Built for **CRM systems and business applications** — software holding customer records, orders, phone numbers and staff accounts — but the skills are stack-agnostic and work on any web project: PHP, Node, Python, Go, Ruby, .NET; PostgreSQL, MySQL, MongoDB; nginx, Caddy, Apache, Cloudflare; VPS, Docker, managed cloud or shared hosting.

Three things it does


1. Finds	Twelve audit blocks over code, git history, database grants, live HTTP surface, dependencies and CRM-specific exposure. Read-only — the audit never changes anything.
2. Explains	Every finding gets four lines: what is open, what could happen because of it, what closes it, how long it takes. No jargon without a plain-language equivalent.
3. Fixes	One layer at a time, each with its own verification step and its own written rollback. Nothing is applied without showing the plan first.