Data & Analytics

Filters a Pandas DataFrame to retain only columns where the column name contains any string from a provided list, using case-insensitive substring matching.

Designs a specific machine learning training architecture using two competing LLMs of different sizes and an objective supervisor to generate preference-optimized datasets based on prospect theory.

Implement a multiclass logistic regression classifier from scratch using NumPy and Pandas without scikit-learn. Use the One-vs-Rest strategy to handle multiple classes (e.g., 0, 1, 2) and save the trained model coefficients to a pickle file.

Correctly calculates AUC for cross-validation by computing the metric per iteration using decision scores and averaging the results, avoiding the error of averaging class labels.

Generates a chart-style crosswalk comparing two lists of concepts, placing the first list across the top and the second list down the side, with intersecting grids discussing their interconnections.

Configures an MLForecast pipeline using LightGBM on Polars DataFrames for weekly time series forecasting. Includes specific lag features (1,2,3,6,12), rolling window statistics (mean/std), and date features, while avoiding expanding means and handling Polars-specific date attribute errors.

Acts as a Data Scientist to generate R code for ranking plant configurations using Random Forest, Gradient Boosting, Neural Networks, and AHP. Also acts as a Thesis Examiner to critique methodology, ask specific questions about hyperparameters and architecture, and suggest improvements.

Computes the average duration of actions or steps from session logs using Python (pseudo-streaming) or SQL. Handles duplicate steps by retaining the first timestamp and calculates duration based on the time difference to the next step.

Automates the process of training multiple neural network instances with varying configurations sequentially and comparing their performance metrics to identify the best model.

Conducts comprehensive market research and competitive analysis for cybersecurity solutions, including product comparisons using a Good/Better/Best matrix, market sizing with specific analyst citations, and pricing details.

Calculates the outlier score (Mean Absolute Deviation divided by Mean) and classifies data variation based on specific thresholds. Provides direct answers without intermediate calculation steps.

Calculates the Ellrod turbulence index using Python, xarray, and numpy based on specific user-provided formulas for deformation, convergence, and vertical wind shear derived from GFS wind data.

Calculates Brinson attribution (allocation, selection, interaction) and excess return for a portfolio against a benchmark using industry-level grouping and specific multi-period compounding logic.

针对数据科学、互联网及游戏行业，提供中英文简历的专业翻译与润色服务。结合HR视角、技术术语规范及特定行业词汇表，确保表达精准、符合招聘标准及目标语言阅读习惯。

Advanced Python visualization expert supporting Pandas DataFrames and raw data. Handles dynamic single/dual-axis plotting, Chinese font configuration, Tensor conversion, and safe file saving without display.

使用mplfinance生成黑色背景的专业K线图，支持白灰涨跌配色、数据自动处理及预测信号叠加。

SOP for extracting and analyzing promotional activity details, handling time formatting, location mapping, payment logic, and step-by-step process validation.

使用mplfinance库从CSV或对象列表生成K线图，支持预测标记（>0.5）、自定义样式、成交量处理及图片保存。

使用 Pandas 和 SQLAlchemy 将 DataFrame 同步到 MySQL，处理 Merge 后缀，并应用复杂的字段比较逻辑（JSON解析、数值归一化、条件排除、字符串排序）以实现精确的 Upsert。

Defines a custom loss function in TensorFlow/Keras where predicting 1 as 0 (False Negative) has zero cost, while predicting 0 as 1 (False Positive) has a cost of 1.

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

🛒 E-commerce & Retail skill suite derived from VoltAgent/awesome-agent-skills. Product catalogue optimisation, conversion rate, customer journey and retail analytics. Provides 10 specialised commands for ecommerce, retail, shopify workflows.

Analyze datasets and generate statistical summaries and insights. Use when asked to analyze data, compute statistics, or identify trends.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx i...