Skill UI

This skill automates the creation of isolated, pre-configured development containers (devcontainers). It scans the project structure to detect supported languages (Python, Node.js, Rust, Go) and intelligently generates the necessary configuration files, VS Code extensions, and setup scripts. It ensures all required tools are installed in a sandboxed environment, making it ideal for starting new multi-language projects or needing consistent, reproducible development workspaces.

Use this command to set up a structured multi-agent collaboration environment within AgentHub. It allows you to define the core task, specify the required number of agents, and configure detailed evaluation criteria (metrics, directions, and commands) for both quantitative benchmarking and qualitative LLM judging. This is the starting point for any agent competition or complex AI workflow.

A comprehensive, multi-phase security audit tool designed to evaluate AI agent skills before deployment. It detects critical vulnerabilities, including prompt injection, malicious code, excessive permissions, secret exposure, and supply chain risks, ensuring the integrity and safety of your agent environment.

This skill automates the complex and tedious process of porting academic papers written in LaTeX from one publisher's journal template (e.g., Springer) to another (e.g., MDPI, IEEE). It executes a structured multi-stage workflow, including content extraction, structural mapping, systematic fixing of common LaTeX issues (like float placement and math environments), and final compilation to ensure the output adheres to the target journal's specifications.

Builds a comprehensive, automated pipeline for malware submission and analysis. It collects suspicious files from multiple sources (EDR, email gateways), automatically submits them to sandbox environments and multi-engine scanners, and generates detailed verdicts and Indicators of Compromise (IOCs). Essential for SOC teams needing to scale high-volume malware triage and incident response.

This skill details the implementation of a cloud-native SIEM and SOAR platform using Microsoft Sentinel. It covers ingesting multi-cloud logs (AWS, Azure, GCP), writing advanced KQL detection queries for threat hunting, and automating incident response workflows using Logic Apps. Ideal for centralized security operations in complex, multi-cloud environments.

A comprehensive guide for authorized penetration testing on detecting and exploiting HTTP Request Smuggling vulnerabilities. It details analyzing discrepancies between Content-Length and Transfer-Encoding header parsing in multi-tier architectures (e.g., CDN, reverse proxy, load balancers). Learn techniques to bypass access controls, capture subsequent user requests, and escalate attacks in a controlled environment.

This skill provides advanced threat hunting capabilities to detect NTLM relay attacks within Active Directory environments. It analyzes critical Windows Security Event 4624 logs, specifically focusing on logon type 3 using NTLMSSP authentication. The detection logic identifies suspicious patterns, including IP-to-hostname mismatches, rapid multi-host authentications, and lack of SMB signing enforcement, helping SOC analysts pinpoint unauthorized credential access attempts.

A comprehensive guide for implementing Cloud Security Posture Management (CSPM) across multi-cloud environments (AWS, Azure, GCP). Learn how to use specialized tools like Prowler and ScoutSuite, combined with native cloud services (Security Hub, Defender, SCC), to continuously monitor for misconfigurations, compliance violations (CIS, SOC 2), and security drifts, thereby enforcing security guardrails in complex cloud architectures.

Perform comprehensive and structured API security testing using Postman. This skill covers testing for OWASP API Security Top 10 vulnerabilities, including authentication bypass, authorization flaws (BOLA), injection, and data exposure. It guides users through setting up multi-role environments, writing automated test scripts for regression testing, and integrating the workflow with CI/CD tools like Newman and OWASP ZAP.

This skill provides a comprehensive guide to implementing secure, defense-in-depth remote access architectures for Operational Technology (OT) and Industrial Control Systems (ICS). It covers best practices such as using jump servers, implementing Multi-Factor Authentication (MFA), session recording, and adhering to standards like IEC 62443 and NERC CIP-005 for vendor and operator access.

Hono is a minimal and ultrafast web framework built entirely on Web Standards (Request/Response/fetch). It allows developers to build high-performance APIs and full-stack applications that run seamlessly across multiple environments, including Cloudflare Workers, Deno, Bun, and Node.js. It is ideal for edge deployment, Backend for Frontend (BFF) layers, and type-safe backend services.