Skill UI

Classifies whether a technology qualifies as an AI system under the EU AI Act Art. 3(1) and determines its risk tier: prohibited, high-risk, GPAI with systemic risk, limited, or minimal risk. Guides users through the scope exclusions, AI definition test, and risk classification workflow.

This orchestrator manages the entire lifecycle of a Claude Managed Agent (CMA). It takes a single, defined goal and deterministically routes the process through specific phases (e.g., interview, grading, scheduled run). It compiles the resulting plan into executable workflows (single-pass, bounded loops, or cron jobs), guiding the user from concept to deployed, scheduled, or iterated agent.

This skill provides a structured workflow to assess compliance with the EU General-Purpose AI (GPAI) Code of Practice and the underlying AI Act (Articles 51-56). It guides users to determine if their model is a GPAI provider, whether open-source exemptions apply, and if systemic risk is present. The assessment details complex obligations across transparency, copyright, and safety requirements for both Tier 1 and Tier 2 compliance.

This workflow implements a bounded, iterative refinement loop for AI agents. It utilizes a required markdown rubric to grade the agent’s output in an isolated context. Based on the grader's verdict, it recommends the next move (sharpen, re-run, or promote). Once the agent passes the rubric, held-back evaluation cases are run in parallel to ensure generalization before final deployment.

This skill orchestrates advanced Machine Learning training workflows on dedicated compute clusters. It manages complex stages (pre-training, fine-tuning, RL) by ensuring strict adherence to immutable manifests, fresh booking entitlements, and multi-step confirmation gates. It acts as a canonical interface for job submission, emphasizing security, idempotency, and resource validation before execution.

Transform a legal professional's bounded knowledge, workflow, or judgment patterns into a safe, structured, and reusable AI skill. This tool processes inputs like legal memos, compliance checklists, or negotiation notes to extract core capabilities, risk taxonomies, and review standards. It strictly separates the extracted capability from the individual's personal voice or identity, ensuring full source traceability and mandatory human review points for high-stakes legal work.

This skill analyzes various legal AI outputs, such as memos, contracts, and reports, to assess their structural integrity and legal robustness. Inspired by Minimum Description Length (MDL), it audits for unnecessary complexity, overly verbose caveats, hidden legal uncertainties, or inefficient workflow design, ensuring the resulting output is as concise and simple as legally safe.

This skill provides a critical audit layer governing the transition of AI-generated legal output from analysis to real-world consequence. It mandates a rigorous check of evidence sufficiency, institutional authority, procedural adherence, and visible uncertainty before any output can become a reliance, recommendation, or executed commitment. It is essential for high-stakes legal workflows, such as contract review, compliance findings, or drafting final advice.

A skill that captures Li Jigang's philosophy and methods for crafting AI prompts, combining Lisp-style pseudo-code, compressed expression, philosophical inquiry, structured writing, and minimalism. Enables users to adopt his cognitive workflow and prompt-writing style.

This workflow mandates external verification for all non-trivial factual claims, ensuring accuracy in high-stakes domains. It is essential when researching current events, legal matters, scientific claims, or providing statistics. The process requires decomposing tasks, searching external sources, and providing immediate, inline citations to support every claim, overriding reliance on internal, potentially outdated knowledge.

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.

Ouroboros is a sophisticated requirement crystallization engine designed for robust AI workflows. It transforms vague, high-level ideas into validated, actionable specifications using advanced techniques, including Socratic interviewing to expose hidden assumptions, generating immutable seed specs, and executing a rigorous 3-stage evaluation (Mechanical > Semantic > Consensus). Ideal for product managers and developers needing to solidify complex AI project requirements.