Skill UI

A specialized guide for assessing whether a storage systems or file system manuscript fits the USENIX FAST conference. It covers venue positioning, required evidence (realistic workloads, fault models), appropriate framing, and comparison methodologies necessary for top-tier systems conference submissions.

Compare multiple Japanese NLP libraries, models, or datasets across selected criteria using a comparison table. Supports both specific tool comparison (seed mode) and topic-based comparison (topic mode). Uses bundled data and web search to find relevant resources. Ideal for evaluating alternatives before choosing the best tool for your project.

A comprehensive guide to building production-grade evaluation systems for Large Language Models (LLMs). This skill covers advanced methodologies, including Direct Scoring and Pairwise Comparison, alongside critical techniques for mitigating systematic biases (e.g., Position Bias, Length Bias). Learn how to select appropriate metrics and structure prompts to ensure reliable, consistent, and objective quality assessment across various AI applications.

Guide to selecting and optimizing embedding models for vector search and RAG applications, covering model comparison, chunking, fine-tuning, and dimension reduction.

This skill helps users find the best AI models for specific tasks by querying Hugging Face benchmark leaderboards. It analyzes hardware constraints like GPU VRAM or CPU memory to filter compatible models. The output includes a comparison table with benchmark scores, parameter sizes, licenses, and device compatibility status. It also suggests whether models can run locally or require API access.

Access comprehensive financial data including income statements, valuation multiples, and company profiles for HK, US, A-share, and Singapore stocks via Longbridge. Supports DCF modeling, value screening, and cross-stock comparison for investment research and business analysis.

Generates SQL validation notebooks for dbt PR changes with before/after comparison queries. Supports GitHub PR URLs and local repositories. Creates interactive notebooks for database validation across Snowflake, BigQuery, Redshift, and Athena. Includes schema inference from dbt_project.yml and model configs.

This skill executes the DeepSWE benchmark, a comprehensive coding-agent evaluation suite. It uses OpenRouter and mini-swe-agent to score various Large Language Models (LLMs) on 113 tasks, providing reproducible results for model comparison, development assessment, and research benchmarking. Use this when a standardized, deep evaluation of LLM coding capabilities is required.