Skill UI

A meta-skill for generating high-quality, publication-ready scientific figures. It guides users through creating complex visualizations, including multi-panel layouts, error bars, significance annotations, and colorblind-safe palettes. It ensures strict adherence to specific journal guidelines (Nature, Science) regarding resolution, file formats (PDF, EPS, TIFF), and typography.

Seaborn is a high-level Python library built on Matplotlib, designed for creating statistically informed and publication-quality graphics. It simplifies complex multivariate data explorations, providing specialized functions for distributions, relationships, and comparisons (e.g., box plots, heatmaps, violin plots). Ideal for data analysis, visualization, and statistical modeling exploration.

SHAP (SHapley Additive exPlanations) provides a unified framework based on Shapley values to interpret complex machine learning models. It calculates feature attributions, enabling users to understand exactly why a model made a specific prediction. This skill supports generating various visualizations (e.g., waterfall, beeswarm, force plots) for feature importance, model debugging, bias analysis, and implementing robust explainable AI across diverse model types like XGBoost, PyTorch, and TensorFlow.

Zarr is a high-performance Python library for storing and manipulating massive N-dimensional arrays. It implements chunking, compression, and parallel I/O, making it essential for large-scale scientific computing pipelines. It offers seamless integration with NumPy, Dask, and Xarray, and provides robust support for cloud storage backends like S3 and GCS via fsspec, ensuring data portability and efficiency.

A comprehensive tool for managing annotation datasets, supporting full CRUD operations, label management, and advanced export functionality. It specifically handles COCO format export and facilitates uploading datasets to platforms like Kaggle, streamlining the data pipeline for AI model development.

This guide provides a quick reference for diagnosing and fixing the top common errors encountered in ClickHouse, including syntax errors, memory limit issues, write permission failures, and data type mismatches. It offers specific error codes, root causes, and actionable SQL solutions for smooth database operation and complex analytics.

This specialized skill provides a robust framework for tracking and updating financial investment signals. It systematically assesses the impact of new market information—such as breaking news or price movements—on existing investment theses. The system determines if a signal is Strengthened, Weakened, Falsified, or Unchanged, providing a crucial layer of continuous signal validation for sophisticated financial decision-making.

A comprehensive skill designed for finance-related information retrieval. It provides dual search capabilities: real-time web searching across multiple engines (Jina, DDG, Baidu) for general market knowledge, and Retrieval-Augmented Generation (RAG) for querying local, proprietary document stores (e.g., daily news). Ideal for financial analysts needing both broad market context and specific internal data insights.

This skill enables searching for stock tickers across A-Share, HK, and US markets. It can retrieve comprehensive historical price data (OHLCV) over specified date ranges, and also fetches crucial fundamental financial metrics such as market capitalization, P/E ratio, and industry sector information. Use this tool when needing to analyze the past or current performance of a publicly traded company.

Provides quick, LLM-optimized summaries for a single academic paper using arXiv IDs or URLs. This skill employs a tiered source fallback system, starting with a structured overview, progressing to full markdown, and finally inspecting the source LaTeX files for deep details. It is designed for rapid comprehension of one specific paper, not for broad literature reviews.

This guide provides production-ready patterns for integrating with Bright Data proxy services. It covers critical aspects like setting up a proxy client, implementing robust retry logic for transient errors (e.g., 502, 503), managing sticky sessions for consistent IPs, and parsing complex HTML responses. Essential for building reliable, high-scale web scrapers using TypeScript and Python.

DeepXiv provides a structured and progressive method for accessing open-access academic literature. Instead of forcing the download of entire papers, it allows users to search by topic or ID and progressively read content—from brief overviews and metadata maps to specific sections. This is ideal for researchers who need layered paper access, trend analysis, or quick, targeted knowledge retrieval without overwhelming context.