Skill UI

This guide provides advanced patterns for composing robust, multi-step Large Language Model (LLM) workflows using LangChain 1.0 core runnables. Learn to implement parallel retrievals (RunnableParallel), conditional routing (RunnableBranch), and state management. It also addresses common pitfalls like silent KeyErrors due to mismatched dictionary shapes, providing solutions using debug probes and type annotations for reliable RAG, classification, and extraction pipelines.

A comprehensive offensive checklist for assessing the security and robustness of AI and Large Language Model (LLM) applications. It covers advanced adversarial techniques such as prompt injection, jailbreaking, model extraction, data poisoning, and analyzing system vulnerabilities across components. Essential for red-teaming and security assessment.

This advanced tool acts as a specialized prompt engineer, guiding users to create highly optimized, production-ready prompts for various AI models (LLMs, Midjourney, etc.). It enforces strict writing rules, guides detailed intent extraction (Task, Context, Constraints), and provides model-specific best practices (e.g., Claude vs. GPT-5.x) to maximize AI output quality and maintain consistency. Essential for professional content creators, developers, and researchers needing precise AI interaction.

A comprehensive tool for searching the Model Context Protocol (MCP) across various GitHub locations, including PRs, issues, and discussions. It allows users to track the full lifecycle of protocol specifications, from initial proposals to final merged changes. Furthermore, it facilitates deep dives into pull request reviews and comments, enabling the extraction of key maintainer rationales and design intent for accurate technical understanding.

This skill provides methods and frameworks to detect sophisticated AI attacks, including model stealing, membership inference, and model inversion. It focuses on monitoring query patterns, analyzing confidence exposure, and implementing defensive controls on inference APIs to protect intellectual property and data privacy.

This skill allows users to extract structured data (text, tables, attributes) from rendered web pages. It enhances traditional web scraping by ensuring all extracted strings pass mandatory AIDefence PII checks and prompt-injection gates before being stored or returned to the model. It supports building reusable extraction templates and running one-shot queries.