Skill UI

This utility implements comprehensive Cloud Workload Protection (CWPP) by monitoring compute workloads on cloud instances (EC2/GCE). It provides runtime security controls, detecting process anomalies, unauthorized binary execution, cryptomining activity, and suspicious network connections using AWS and Google APIs. Ideal for establishing robust security postures and meeting compliance requirements.

This guide details how to implement advanced SIEM correlation rules to detect sophisticated Advanced Persistent Threats (APTs). By chaining multiple event types—including Windows authentication events, process execution telemetry, and network connection logs—across hosts, users can surface complex attack sequences that are invisible to single-event detections. It utilizes Splunk SPL and Sigma rule formats for robust security posture enhancement.

Automates the static security analysis of Android APK/AAB files using the Mobile Security Framework (MobSF). This skill identifies critical vulnerabilities such as hardcoded secrets, insecure permissions, weak cryptography, and structural flaws (mapping to OWASP Mobile Top 10) without requiring application execution. It is essential for integrating security gates into CI/CD pipelines, performing pre-release quality assurance, and enhancing penetration testing coverage.

This guide provides a comprehensive methodology for performing directory traversal and path traversal testing on web applications. It covers identifying file path parameters, executing basic payloads (Linux/Windows), bypassing common security filters using encoding (URL, double, UTF-8), and automating the process with tools like ffuf and dotdotpwn. It also details advanced steps for local file inclusion (LFI) and potential escalation to Remote Code Execution (RCE) via log poisoning.

This skill details advanced techniques for performing stealthy lateral movement across Windows domains using Windows Management Instrumentation (WMI). It covers the abuse of native tools like Impacket's wmiexec.py and CrackMapExec, enabling remote command execution, Pass-the-Hash attacks, and fileless techniques, crucial for authorized red team engagements and security auditing.

CCPM orchestrates software delivery from PRD through epics and GitHub issues into parallel agent execution, covering planning, decomposition, syncing, workstart, and status checks with mandated script-based reporting.

A lightweight CLI tool for systematically comparing various coding AI agents (such as Claude Code, Aider, and Codex) head-to-head. It measures crucial metrics—pass rate, API cost, execution time, and consistency—on reproducible tasks defined via YAML manifests. Use this to objectively select the best agent for your codebase or to validate model updates before production deployment.

This skill systematically audits a given project by analyzing its historical memory, rollout summaries, and local skill definitions. It identifies repeated complex workflows, recurring operational patterns, or areas where existing skills are stale. The audit process guides the user to recommend the highest-value skills to either add (if a new pattern emerges) or update (if current skills are outdated or incomplete), ensuring the AI agent operates with the most accurate and context-specific knowledge base for optimal project execution.

A comprehensive guide on implementing advanced security observability using eBPF and Cilium Tetragon. This skill covers real-time tracking of process execution, network connections, and file system access directly in the kernel. Learn how to author TracingPolicy CRDs, utilize kprobe/tracepoint hooks for in-kernel filtering, and enforce runtime security policies (e.g., process killing) on Linux hosts or Kubernetes clusters.

A comprehensive guide and technical framework for detecting and mitigating ransomware kill switch mechanisms. It details methods for analyzing mutex guards, domain-based communication, and registry checks. Learn how to deploy proactive mutex vaccination and use Sysmon/DNS monitoring to prevent malware execution during incident response and analysis.

AgentFlow transforms your existing Kanban board (Asana, GitHub, Linear) into a self-managing, autonomous AI development pipeline. It orchestrates multiple AI agents through defined stages (Backlog to Done), enforcing deterministic quality gates, performing adversarial reviews, and tracking costs—all visible within your existing project management UI. It provides crash-proof execution and full observability for complex software development lifecycles.

This skill guides users through evidence-based terminal operations. It is designed for scenarios requiring direct command execution, Git status checks, debugging CI/build failures, and pushing narrow, verified fixes. It emphasizes following a structured, minimal-scope workflow and accurately reporting the repository's current state (e.g., local changes vs. pushed code).