Skill UI

NeMo Curator streams GPU-accelerated curation for LLM training, with super-fast fuzzy deduplication, multimodal quality filters, semantic dedupl, PII redaction, NSFW checks, and RAPIDS-scaled pipelines for prepping massive corpora.

Implements a robust, multi-factor model to calculate the criticality score of IT assets. The scoring incorporates data sensitivity, business function dependency, regulatory scope, and network exposure, moving beyond simple CVSS scores. The resulting 1-5 criticality tier directly modifies vulnerability remediation Service Level Agreements (SLAs), ensuring security resources are focused on the organization's most valuable and risky systems.

This skill enhances research query formulation by translating vague, colloquial, or generalized descriptions into precise, standard academic terminology. When initial search terms are broad (e.g., "conjugal happiness"), this technique suggests multiple plausible academic synonyms (e.g., "marital satisfaction," "relationship quality"). By improving the precision of the search query and incorporating structured constraints (like keywords, years, or sample sizes), it significantly boosts the relevance and effectiveness of academic paper retrieval.

This guide teaches advanced methodology for identifying target species using multiple biological features. Users learn to combine distinct clues such as habitat, morphology, behavior, and geographic range. A key technique involves first identifying the country through demographic clues (e.g., population growth, endemic status) to significantly narrow the search scope before searching for the specific species.

A powerful tool for deterministic and reproducible retrieval of evidence from specialized academic and policy corpora. It supports searching arXiv (preprints), PubMed/PMC (biomedical literature), and US policy documents. Users can check corpus freshness, retrieve stable metadata, and fetch full-document Markdown for high-reliability research tasks.

A robust API-backed skill for fetching YouTube transcripts, searching video content, browsing channels, and extracting playlists. It functions reliably from any cloud server environment, bypassing limitations found in local tools like yt-dlp or reliance on Google API keys. Ideal for building research corpora, competitive intelligence monitoring, and systematic content analysis.

This utility reads structured JSON outputs from multi-search-engine APIs (e.g., Google Scholar, arXiv) provided via standard input. It converts these normalized records into a clean, minimal BibTeX format, suitable for academic papers. It intelligently preserves crucial metadata like DOI, authors, and years while automatically handling data sanitization, deduplication of DOIs, and protecting complex fields like corporate names.

This skill provides deep, cross-border financial analysis and valuation metrics for stocks across multiple markets (e.g., US, HK). Users can access detailed income statements, balance sheets, cash flow data, analyze business segments, compare valuation multiples (PE, PB), run sophisticated DCF models, and perform value screening. It is an essential tool for fundamental research, investment modeling, and corporate analysis.

This plugin provides advanced vector search capabilities using two distinct paths. The large-scale path supports millions of vectors via HNSW, ideal for general corpus search. The hot-path router handles small, critical pattern routing (≤11 patterns) with sub-ms latency. Key features include RaBitQ 1-bit quantization for memory efficiency (32× reduction), hyperbolic space search for hierarchical data, and unified cross-namespace search.

A comprehensive guide for designing rigorous and robust empirical programs in Information Retrieval, Data Mining, and Knowledge Management. It outlines how to meet the stringent evidence requirements for top-tier conferences, ensuring claims are substantiated across multiple evaluation dimensions (retrieval, mechanism, scalability) and incorporating best practices for reproducibility and handling modern challenges like LLM contamination.

This guide outlines rigorous standards for incorporating theoretical and quantitative models into economic policy manuscripts. It emphasizes that models must be minimal, transparent, and directly bear policy weight—converting estimates into statements about welfare, fiscal costs, or clear mechanisms. It teaches how to design models that pass 'the necessity test,' ensuring policymakers can trace headline numbers directly back to key, identifiable assumptions.

This guide outlines advanced econometric strategies and best practices for establishing causal identification in corporate finance and asset pricing. It addresses common methodological pitfalls, such as endogeneity, spurious correlation, and weak designs, providing specific techniques (e.g., staggered DiD, robust IV inference) required to defend a research paper's claims to top-tier academic journals.