Skill UI

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

Prepares Claude with an ultra-granular, line-by-line code-analysis mode that maps invariants, assumptions, and flows before any vulnerability hunting, keeping context stable and reducing hallucinations during audits.

Generates complete, production-ready Google Cloud Platform (GCP) code examples and infrastructure templates. It spans various modern AI patterns, including ADK agents, Genkit RAG flows, and multimodal analysis using Vertex AI and Gemini. The output includes runnable code, deployment configuration (Terraform/IaC), security best practices (IAM, VPC-SC), and monitoring setup, ensuring enterprise-grade reliability and cost optimization.

ZAI CLI provides comprehensive access to Z.AI's advanced capabilities, including image/video analysis, real-time web search, web page extraction, and GitHub code exploration. It is designed for users needing multi-modal content analysis, error diagnosis, and complex data processing through a unified command-line interface. Ideal for developers and analysts requiring robust, API-driven AI functionality.

Coordinates Exa MCP-driven web_search_exa and get_code_context_exa calls for up-to-date web results, code snippets, and company or people intel whenever the user requests research, competitive analysis, or development context.

Detect malicious scheduled task creation and modification using Sysmon (Event IDs 1/11), Windows Security events (4698/4702), and correlation of suspicious parents, public paths, and encoded arguments for persistence and lateral movement analysis.

This skill provides comprehensive interaction with the DeerFlow AI agent platform via its robust HTTP API. It is designed for managing complex, multi-step AI workflows, including deep academic research, code execution, web browsing, and file analysis. Users can initiate and continue conversation threads, manage agent memory, upload documents (PDF, etc.), and delegate complex research tasks to the autonomous agent system.

Phoenix Evals lets teams build evaluators for AI/LLM apps by wiring deterministic code with LLM nuance, running Python or TypeScript workloads, validating against humans, and iterating through error analysis, RAG, and production workflows.

Generates comprehensive, long-form cheat sheets for advanced Machine Learning and Large Language Model (LLM) topics. Each sheet includes detailed mathematical derivations, from-scratch, runnable PyTorch code implementations, comparative analysis tables, and 25 tiered interview questions (L1-L3). Ideal for deep academic review and technical interview preparation.