Skill UI

This comprehensive tool validates Claude Code plugins against official Anthropic specifications and internal enterprise standards. It performs two main types of checks: structural validation (checking `plugin.json` fields, file references, and permissions) and content validation (conducting deep grading using `SKILL.md`). Use this when building, auditing, or preparing plugins for marketplace submission to ensure compliance and quality.

Guides founders on AI positioning, ICP definition, messaging architecture, and quarterly PMF validation so they can translate technical capabilities into the business outcomes buyer-facing teams care about.

A specialized threat hunting skill designed to detect remnants of the PowerShell Empire post-exploitation framework. It analyzes Windows event logs (specifically Script Block and Module Logging) for key Indicators of Compromise (IOCs), such as default launcher strings, Base64 encoded payloads, known module signatures (e.g., Mimikatz), and staging URL patterns. The output provides a detailed JSON report, comprehensive timeline, and MITRE ATT&CK mapping for incident response and security validation.

This skill provides a comprehensive workflow for building vendor-agnostic detection rules using the Sigma format. It empowers security operations center (SOC) engineers to translate raw threat intelligence and MITRE ATT&CK techniques into standardized, portable detection logic. The process guides users through rule validation and conversion into specific queries for major SIEM platforms, including Splunk, Elastic, and Microsoft Sentinel, ensuring robust detection coverage.

This skill outlines a comprehensive, structured workflow for managing Microsoft Patch Tuesday security updates. It covers the entire lifecycle, from initial vulnerability triage and risk assessment to testing, staged deployment (Pilot, Production Rings), and final validation, ensuring compliance with risk-based remediation SLAs.

This utility provides a comprehensive framework for proactive threat hunting, focusing on detecting advanced and suspicious PowerShell execution patterns. It covers common attacker techniques such as encoded command usage, download cradles (IEX), AMSI bypass attempts, and constrained language mode evasion. It is designed for security analysts during incident response and threat intelligence validation, requiring EDR and SIEM telemetry.

A comprehensive framework for penetration testing APIs, designed to detect and exploit critical injection flaws. It covers SQL injection (SQLi), NoSQL injection, OS command injection, LDAP injection, and Server-Side Request Forgery (SSRF). This skill guides the testing of all input vectors—including path parameters, headers, query strings, and request bodies—to assess input validation and backend security posture against industry standards like OWASP.

This tool simulates various BGP hijacking scenarios, including prefix hijacking and route leaks, within authorized, isolated lab environments. It is designed to assess the effectiveness of critical network defenses such as RPKI deployment, route origin validation, and BGP monitoring systems against unauthorized route announcements. It is a training and validation tool for network operations teams.

A comprehensive skill for assessing mobile applications (Android and iOS) for vulnerabilities related to deep links, custom URI schemes, and intent handling. This skill identifies risks such as unauthorized access, data injection, intent hijacking, and improper validation of App Links or Universal Links, crucial for robust mobile security testing.

A comprehensive guide detailing the Kerberoasting technique (T1558.003) used in Active Directory environments. This method exploits service accounts by requesting and subsequently cracking Kerberos TGS tickets offline, allowing attackers to compromise credentials. Instructions cover enumeration, ticket request, cracking with tools like Hashcat/John the Ripper, and credential validation, for authorized red team and penetration testing purposes.

The Metasploit Framework is the industry standard platform for penetration testing and vulnerability validation. It provides numerous modules (exploits, payloads, auxiliaries) used to confirm if identified security weaknesses are genuinely exploitable. This guide details using Metasploit in a structured, risk-based workflow for authorized testing, including vulnerability checking, post-exploitation assessment, and patch verification.

Provides a structured methodology for proactive threat hunting against Living-off-the-Land Binaries (LOLBins). It guides practitioners in identifying techniques where adversaries abuse legitimate system tools (like certutil, mshta, rundll32) to execute payloads while bypassing traditional security controls (AV/EDR). Ideal for incident response, red team validation, and improving detection coverage against fileless attacks.