Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Evaluate AI agents by preparing test cases, scoring responses and tool use, investigating failures, and comparing results after changes. Supports built-in checks and custom scoring rules, including evaluations performed by a language model.
Answer business questions about counts, trends, comparisons, or rankings using SQL, a language for querying tables. Validate the results, then present a concise answer, a small table, the executed query, and supporting checks.
Turn analysis results into charts suited to the question, such as trends, comparisons, or distributions. Save a chart image and the script that generated it, with a short explanation of the findings and relevant caveats.
Calculate the count, sum, minimum, maximum, and average of supplied numbers or datasets, then present the results in a clear, structured format. Analysis results can also be saved to a file when requested.
Create and refine YAML prompts for AI assistants using structured roles, requirements, and output instructions. Organize reusable templates with variable placeholders, and check indentation, braces, headings, and formatting for consistency.
Guides the design of data pipelines, continuous stream processing, and data quality checks. It compares tools such as Airflow, Dagster, and Flink, and provides implementation patterns and checklists for scheduling, retries, validation, and monitoring.
Routes AI development questions to focused references on agents, language model security, retrieval-augmented generation, which uses retrieved information in answers, and prompt design and evaluation. It also outlines principles for validation, safety boundaries, version control, and ongoing assessment.
Extract data from websites or saved HTML using a suitable fetching method for each page. The skill generates and runs scripts for static pages, form-based logins, JavaScript rendering, and sites with Cloudflare or WAF protection.
Combine data from multiple Excel sheets, clean inconsistent labels and merged cells, and summarize counts by category. Create Excel summary tables with percentages and totals, plus labeled bar charts for comparing categories.
Clean Excel data and group records with similar numerical features. Produce a combined view of indicator trends, value distributions, category shares, and grouped data, then export the charts as an image and cleaned records as Excel.
Calculate averages for selected groups in Excel and sum items extracted from specified row ranges after removing duplicates. Save filtered records, summary statistics, and item totals as Excel files with local download links.
Clean a target Excel column, convert its values to numbers, and compare the calculated total with a summary sheet. Export the totals, match status, and difference in Excel and CSV files.
Turn Excel or CSV data into an Excel report with category totals, percentage shares, and a doughnut chart. The workflow identifies likely category and numeric columns, cleans missing values, and highlights the largest share.
Clean category and numeric fields in structured data, compare groups with counts and cross-tabulations, and produce charts, Excel results, and a Markdown report. Export visuals as high-resolution PNG and SVG files for use in reports.
Group Excel figures by department or product line, assign performance tiers, and calculate projections using growth rates set for each tier. Compare current and projected values in charts and summarize overall growth for target setting.
Filter rows from Excel or previously converted Parquet files, a format designed for efficient data storage. Summarize matching records by group with counts, percentages, and totals, then export the summary to Excel.
Extract keyword-matched entries from an Excel sheet, clean whitespace and empty values, and count distinct entries by category. Export separate Excel files containing summary counts and detailed lists for review.
Count rows across Excel sheets to assess data size, then analyze an existing Parquet file, a format for storing tabular data. Calculate category counts and percentages, and save the results as an Excel summary and a pie chart.
Extract selected ranges from Excel workbooks with multiple sheets, check missing values, and clean numeric data. Fit a straight trend line, save charts and CSV results, and convert larger tables to Parquet for subsequent analysis.
Combine selected columns from multiple Excel sheets, fill blank category cells with the preceding value, and rank records by a chosen metric. Export the top results to an Excel report with headings, borders, and formatted numbers.
Clean Excel data, summarize groups, and examine relationships between numeric columns. Produce charts such as scatter plots with trend lines, calculate measures of fit and statistical significance, and export cleaned data and statistical summaries.
Prepare large Excel datasets by combining sheets, using Parquet, a format for efficient table storage, and cleaning a selected text column to retain only Chinese characters. Export the cleaned data as an Excel file with a local download link.
Filter Excel rows using conditions across several numeric columns. Count rows across sheets, convert selected fields to numbers, remove duplicate rows and records with missing identifiers, then export the filtered results to a new workbook.
Analyze large Excel workbooks by totaling values by category and identifying the highest result. The workflow can convert data to Parquet, a column-based storage format, and export a styled Excel report with highlighted results.