Skill UI

NVIDIA’s NeMo Guardrails adds runtime safety rails to LLM apps, covering jailbreak detection, hallucination and fact-checking, PII filtering, and toxicity checks via Colang 2.0 rules and integrations for production use on T4 GPUs.

This workflow executes a single-query search using the Perplexity Sonar model, ensuring all returned answers are web-grounded and accompanied by inline citations. It is essential for building high-trust applications, fact-checking tools, or any system requiring verifiable, real-time information retrieval. The process includes API interaction, detailed response parsing (answer, citations, search results), and formatting the output into a usable, source-linked format.

AI-powered search using Perplexity models via LiteLLM and a single OpenRouter API key for real-time, web-grounded answers with citations, ideal for up-to-date research, literature surveys, fact checking, and domain-specific queries beyond model cutoffs.

A comprehensive guide for safely upgrading and migrating between Apify core packages, including apify-client, apify, and crawlee. This skill is essential for handling major breaking changes, particularly the transition from Apify SDK v2 to v3, which separated crawling functionality into the dedicated 'crawlee' package. It provides detailed steps for version checking, dependency management, and code refactoring.

A domain-agnostic 13-agent pipeline for rigorous academic research on any topic. Eight modes cover full research, quick briefs, paper review, literature review, fact-checking, three-way literature scans, Socratic research dialogue, and systematic review with optional meta-analysis, from question formulation to APA 7.0 reporting.

A comprehensive tool for sanity-checking research questions intended for Information Systems Research (ISR). It guides users to test the topic's fitness across four dimensions: IT-artifact centrality, sociotechnical framing, intradisciplinary potential, and level of analysis. It helps determine if the topic belongs in ISR or neighboring venues like MISQ or JMIS.

A comprehensive skill for researchers targeting top international economics journals, such as the Journal of International Economics. It provides detailed guidelines on content fit, structuring arguments, required quantitative modeling rigor (e.g., credible identification, counterfactuals), and adherence to current academic house styles for international trade, open-economy macro, and finance research. Use this for venue selection and pre-submission self-checking.

This skill maps chronic conditions extracted from clinical notes to CMS-HCC V28 categories. It estimates the Risk Adjustment Factor (RAF) score, which is crucial for Medicare Advantage payments. It serves as decision support for coders by identifying candidate HCCs, applying complex coding hierarchies, and checking for MEAT documentation evidence for human validation.

This comprehensive skill allows users to search the web using the DuckDuckGo API, retrieving diverse content including text results, news articles, images, and videos. It supports advanced filtering options such as time range, region, content type (e.g., news, images), and specific media characteristics (e.g., image size, video duration). Ideal for research, fact-checking, academic study, and gathering current web resources.

This skill forces the AI to operate in a non-inferential mode, ensuring every claim—factual, legal, or numerical—is strictly anchored to user-provided materials or verified online sources. It eliminates assumptions, gap-filling, and background knowledge reliance, making it essential for legal research, evidence review, citation checking, and high-stakes document analysis where evidential fidelity is paramount.

A rigorous multi-pass editor for law review articles, student notes, seminar papers, and other legal scholarship. It runs six specialized passes covering structure, substantive critique, Bluebook citations, grammar, fact-checking, and synthesis, delivering a prioritized editorial memo. Handles articles of any length via intelligent chunking and reads .docx directly.

This skill performs a comprehensive architecture audit on codebases by mapping module dependencies and checking layering integrity. It identifies structural decay using principles from classic engineering books. The tool generates Mermaid dependency graphs, assesses testability seams, and applies Conway's Law checks to ensure architectural health. It is suitable for developers needing to understand codebase structure, review folder organization, or detect circular imports before refactoring.