CSV

The xlsx skill helps agents read, edit, repair, create, and convert .xlsx, .xlsm, .csv, and .tsv files when the required deliverable is a spreadsheet. It is strongest for template-preserving updates, formula-safe workbook edits, messy tabular cleanup, and practical spreadsheet workflows backed by repo scripts for packing, validation, and recalculation.

The user-personas skill creates 3 refined personas from research data with JTBD, pains, gains, and unexpected insights. Use it for user-personas for UX Research, segmentation, onboarding strategy, and product decisions when you have surveys, interviews, or other source material.

The sentiment-analysis skill turns user feedback into segment-level insights, sentiment scores, JTBD, and product impact. Use it for sentiment-analysis for Data Analysis on reviews, surveys, support notes, or social listening when you need a practical sentiment-analysis guide, not a generic polarity check.

Perform cohort-analysis on user retention, engagement decay, and feature adoption by cohort. This cohort-analysis skill is built for Data Analysis workflows that need validation, calculation, visualization, and clear insights from structured user behavior data.

ab-test-analysis helps you evaluate A/B test results with statistical rigor, including sample size validation, confidence intervals, significance testing, and ship/extend/stop recommendations. Use it for experiment review, split-test interpretation, and decision-making for Data Analysis workflows.

Workspace Data Analyst is a lightweight skill for data analysis in your workspace. It analyzes CSV files, checks headers, summarizes totals, averages, and outliers, and provides concise next-step insights. The Workspace Data Analyst skill is ideal for quick file-aware reviews before deeper modeling.

read-file helps an agent read and inspect CSV, JSON, Parquet, Avro, Excel, SQLite, spatial files, or remote URLs with DuckDB. Use it to preview rows, check schema, profile data, and answer what’s in this file. It’s best for read-file usage on real data artifacts, not source code.

The query skill runs DuckDB queries against an attached database or directly against files. It accepts SQL or natural-language questions, supports session and ad-hoc modes, and is useful for Data Analysis, quick checks, and iterative query work with DuckDB Friendly SQL.

The minimax-xlsx skill helps create, read, edit, validate, and format Excel workbooks with an Excel-first workflow. Use minimax-xlsx for Spreadsheet Workflows when you need structured files that preserve formulas, styles, sheet layout, and workbook behavior. It supports .xlsx, .xlsm, .csv, and .tsv tasks, including analysis, new workbook creation, minimal-invasive edits, formula repair, and validation. The minimax-xlsx guide is designed for real workbook handoff, not flat tables.

chdb-datastore is a pandas-compatible skill for fast data analysis with a ClickHouse-backed DataStore API. It supports file, database, and cloud connectors, cross-source joins, and minimal code changes for pandas-style workflows. Use this chdb-datastore guide when you want a drop-in analysis layer for larger datasets.

chdb-sql is a GitHub skill for running ClickHouse SQL in Python without a server. It covers chdb.query(), Session, DB-API connections, table functions like file() and s3(), parametrized queries, and backend development workflows for local files and external data sources.