Skill UI

A systematic methodology for performing offensive cryptographic analysis. This skill focuses on identifying and exploiting flaws arising from the misuse of cryptographic primitives in real-world applications, rather than breaking the underlying math. Techniques covered include Padding Oracle Attacks (CBC), ECB block manipulation, Hash Length Extension, RSA weaknesses, and PRNG exploitation. Ideal for penetration testing and deep security auditing.

A comprehensive guide for authorized red team and penetration testing engagements, detailing techniques that exploit human trust and psychological vulnerabilities. Coverage includes pretexting, vishing, smishing, physical access attacks (e.g., badge cloning, tailgating), USB payload delivery, and OSINT-driven targeting. This methodology maps to key MITRE ATT&CK T-numbers, simulating real-world, multi-vector adversaries to test organizational defenses at the human layer.

This tool simulates an experienced opposing counsel, providing a deep, adversarial analysis of legal arguments, submissions, or statements. It goes beyond mere critique, generating a six-part structure: a core theory of attack, structural deconstruction, primary lines of flaw (e.g., evidential gaps, legal misstatements), and high-impact points for oral submissions. Ideal for stress-testing legal writing before litigation.

A comprehensive AI sparring partner designed to prepare lawyers for high-stakes adversarial proceedings, such as oral arguments, depositions, or hearings. It profiles judges/arbitrators based on their prior opinions and questions, predicts likely lines of questioning, maps narrow 'escape routes' they can take, and simulates relentless, real-time adversarial questioning to sharpen arguments until only the strongest answers survive.

A comprehensive utility for managing the global configuration of the Ouroboros system. This tool allows users to adjust per-stage runtime parameters, select global models, configure the LLM backend, and manage agent definitions. It supports multiple interaction modes, including graphical user interfaces (browser/TUI), remote SSH environments, and conversational chat interfaces, ensuring consistent setup regardless of the deployment context. Ideal for optimizing complex AI agent workflows.

Runs a structured adversarial premortem simulation for UK civil litigation. It builds the strongest version of the case and then attacks it from four critical angles (procedural, substantive, evidentiary, strategic) to pinpoint exact failure modes and blind spots before opposing counsel does. Essential for pre-issue planning, settlement strategy, and litigation fund pitches.

This advanced skill provides systematic, adversarial verification for AI-generated legal documents. It rigorously checks factual accuracy, legal citations, numerical data, and source authenticity against authoritative databases. Use this when you need to perform red-teaming, fact-check, or quality-control complex legal analyses, compliance reports, or regulatory summaries before any external distribution.

A comprehensive tool for managing scope across the entire lifecycle of a legal matter. It helps legal teams establish a baseline scope, proactively track all out-of-scope (OOS) activities, draft necessary client communications, and manage scope creep. By automating capture and surfacing confirmations, it transforms scope management from an adversarial task into a professional, client-focused service, preventing budget surprises and ensuring project alignment.

This meta-skill automates the entire short-drama production pipeline, starting from a simple topic. The workflow analyzes the request to infer render style, character identity, and shot count. It first drafts a detailed, shot-by-shot shooting script and pauses for user review. After approval, it generates a universal cast reference image, per-shot composition images, and corresponding video clips. Crucially, it maintains character and scene consistency by anchoring every video to both the reference image and the composition image. Finally, it adds title/ending cards, burns subtitles, and de...

skill-doctor grades the performance and quality of an AI agent setup using real, local conversation history (e.g., Claude Code/Codex sessions). It scores skills against defined rubrics for efficiency and code quality, drafts evidence-backed suggestions for improvement, and generates a comprehensive, shareable local report. All processing is strictly local and private.

This advanced skill stress-tests legal submissions, motions, or arguments by generating an adversarial critique that survives multiple layers of challenge. It goes beyond superficial attacks, ensuring every point is load-bearing and defensible against a single-sentence reply. Ideal for red-teaming, stress-testing, or refining arguments to withstand rigorous scrutiny.

A rigorous, standalone tool designed for explicit, blind, and adversarial code review. It executes the code target through two parallel, independent judges (Judge A and Judge B) with strict rules and limited fix rounds. This process ensures maximum scrutiny, providing a definitive, highly corroborated verdict (APPROVED or ESCALATED) that replaces standard review methods.