Skill UI

This tool initializes a dedicated AgentHub session for multi-agent collaborations. It requires defining the core task, specifying the number of parallel agents, and configuring detailed evaluation criteria (including the evaluation command, target metric, and measurement direction). Upon execution, it generates a unique session ID and prepares the entire environment for subsequent agent spawning and competitive evaluation, optionally capturing a performance baseline.

This skill manages the human-in-the-loop verification phase of an agent workflow. It ensures that critical artifacts—such as plans, specifications, or migrations—receive mandatory, structured human sign-off before being considered complete or shipped. It collects severity-graded, machine-parseable feedback (e.g., BLOCKER, MAJOR) and acts as a strict gate, preventing completion until all objections are resolved and the review is formally signed off.

This skill provides an expert framework for conducting comprehensive legal gap analyses between European Economic Area (EEA) law and Icelandic national legislation. It guides users through identifying transposition delays, inconsistencies, and compliance risks by systematically comparing EU directives, Joint Committee Decisions, and specific Icelandic statutes, ensuring thorough assessment of adherence to EEA obligations.

This skill establishes a rigorous, verification-first methodology for citing jurisprudence from the ICTY, ICTR, and IRMCT. It mandates multi-level checks (existence, content, paragraph) against authoritative databases (irmct.org, UCR) and sources to ensure legal claims are accurate and non-misrepresentative. It guides users through a structured workflow for high-stakes legal research.

Provides IDA Pro reverse engineering capabilities for analyzing binaries, PE/ELF/APK/DLL/SO files, firmware, and malware. Supports decompilation, password discovery, vulnerability analysis, and software cracking workflows. Uses deterministic scripts for HTTP server management and file opening to avoid known MCP schema and lock issues.

This skill guides users through a structured, Socratic interview process to transform vague, high-level operational ideas into actionable, clear specifications. It incorporates advanced capabilities like lateral thinking review, ambiguity tracking, and iterative refinement, ensuring that all constraints and decisions are explicitly documented before development can begin.

This methodology guides developers to diagnose ambiguous failures, intermittent bugs, or performance regressions before implementing any code changes. It emphasizes separating observed symptoms from inferred causes, tracing inputs and state transitions, and ranking hypotheses based on evidence and cheap falsification value. Use this structured approach to ensure fixes are built upon a proven mechanism.

An expert advisor for implementing, auditing, and achieving certification under ISO/IEC 42001:2023. This skill guides organizations (AI providers and users) through establishing an AI Management System (AIMS). It covers critical areas including AI risk assessment, AI impact assessments, responsible AI principles, governance framework setup, and preparing for formal ISO certification.

This skill simulates the experience of a senior judge reviewing a written legal argument, submission, or academic paper for the first time under time pressure. It provides a structured, objective assessment of clarity, structure, and persuasive force, detailing areas of confusion, perceived strengths, and unproven assumptions without suggesting revisions or improvements. Ideal for refining core legal and policy arguments.

This document serves as a comprehensive reference for credential store terminology and access policies. It details how credentials are securely managed and accessed within the system, helping users understand the rules governing sensitive data storage.

This skill helps legal professionals set up a personalized, structured Legal Guidance Vault. It guides the user through an interview of their entire digital tool stack (email, calendar, docs, etc.) to ensure all sources are covered. It generates a standardized, reusable prompt template for archiving privileged legal advice, making it searchable by topic, person, or product in future sessions.

This sophisticated skill assists in-house legal teams with comprehensive legal risk assessment and classification. It uses a structured framework based on severity and likelihood, but critically, it enforces a rigorous three-step research methodology: adversarial searching for contradicting case law, systematic doctrinal web searches for context, and a temporal confidence check to ensure legal positions are current. It ensures that risk assessments are grounded in the most reliable and updated legal landscape.