Skill UI

A 12-agent pipeline for writing academic papers across all disciplines. Supports 11 modes including full drafting, outlining, revision coaching, literature review, citation checks, AI disclosure, and conference rebuttal audits, with LaTeX, DOCX, and PDF output.

This skill helps researchers strengthen AAAI paper submissions by ensuring reproducibility standards are met. It covers experimental traceability, seed reporting, compute disclosure, and dataset licensing. Users learn to map claims to evidence, audit checklists, and prepare artifacts for Phase-1 reviewers to validate rigor across AI scopes.

A comprehensive guide detailing the mandatory submission requirements for major AI conferences like CIKM. It covers critical areas such as strict page budget rules (including appendices), mandatory GenAI Usage Disclosure, EasyChair nomination processes, maintaining double-blind anonymity, and adhering to crucial deadlines like the abstract-gate week to prevent desk rejection.

A comprehensive guide for researchers detailing how to strengthen the reproducibility of AI/ML papers for top-tier conferences like ICML. It provides an evidence checklist covering data sources, anonymized code, random seeds, compute budget disclosure, and theoretical assumptions, ensuring claims are robust and verifiable.

This guide details advanced best practices for achieving scientific reproducibility in probabilistic modeling and deep learning research. It mandates rigorous disclosure of seeds, hyperparameters, diagnostic traces (e.g., R-hat, ELBO), and compute environments to ensure that all claims made in academic papers are verifiably backed by traceable evidence. It elevates reproducibility from a simple code run to a comprehensive audit.

Assesses Art. 50 transparency duties under the EU AI Act for a provider/deployer. Covers chatbot disclosure, synthetic-content marking, emotion-recognition notices, machine-readable marks, exceptions, deadlines. Produces mini-report with compliance checklist and gap flags.

An advanced AI co-counsel designed for family and divorce law attorneys. This scaffold assists with the entire matter lifecycle—from intake and financial disclosure to drafting, mediation, and court preparation. It supports structural analysis, document organization, and strategy, while maintaining strict ethical boundaries and emphasizing attorney oversight. It is designed to be jurisdiction-agnostic, handling various personal-status regimes.

This skill covers the core concepts of context engineering for language models, including system prompts, tool definitions, retrieved documents, message history, and tool outputs. It explains attention mechanisms, context windows, and progressive disclosure principles to help optimize agent performance and reduce token costs during inference.