References

References extends your AI assistant with the ability to comprehensive security audit skills. Check file permissions, environment variables, dependency vulnerabilities, configuration files, network ports, Git security, Shell security, macOS security, key detection, and more. Supports CLI parameters, JSON output, configuration files. Use this skill when the user requires "security check", "vulnerability scan", "permission check", and "security audit". Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly — and it will take care of the task end-to-end, using References as its underlying capability.

References works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) — an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install References once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.

Getting started with References takes about two minutes. Place the skill at `~/.claude/skills/references/` (personal, all projects) or `.claude/skills/references/` (project-specific), then restart your AI client. From that point, typing `/references` in any conversation activates it, or the AI will use it on its own when it detects a relevant request.

References has 252 installs and is part of the growing Developer & DevOps skill ecosystem on DiscoverAISkills. The source code is open on GitHub — you can inspect it, contribute fixes, or fork it to adapt the skill for your specific setup. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.