Back to Skills Marketplace
Skill pack

Data Analysis Lab

Profile CSV/JSON datasets, detect data quality issues, compute summaries, and prepare spreadsheet-ready analysis.

v0.1.0 1 skill 6 tools By Kendr dataanalysiscsvjsonspreadsheetbusiness
Publisher docsHosted archive

How to use it

  1. Open Kendr Desktop.
  2. Go to Skills, then Marketplace.
  3. Search for Data Analysis Lab or data-analysis-lab.
  4. Install the pack, then enable the pack or individual skills you want available in agentic mode.

Kendr Desktop compares the installed version with the hosted catalog version and offers an update when this pack changes.

Install source

Use this hosted archive when installing or updating the pack from Kendr Desktop.

https://kendr.org/api/skills/packs/data-analysis-lab/archive

Data Analysis Lab

Analyze CSV, TSV, JSON, and JSONL datasets with profiling, quality checks, numeric summaries, grouped summaries, correlations, and spreadsheet-ready recommendations.

Data Analysis Lab

Use this skill when the user asks for data analysis, CSV/JSON exploration, spreadsheet analysis, KPI summaries, data quality checks, trends, cohorts, or a workbook-ready analytical summary.

Prefer inspection first:

  • use data-analysis.inspect_dataset to understand columns and sample rows
  • use data-analysis.profile_dataset before making assumptions about field meaning
  • use data-analysis.find_data_quality_issues before reporting final conclusions
  • use data-analysis.summarize_numeric_columns, data-analysis.compute_grouped_summary, and data-analysis.correlation_matrix for quantitative analysis

For outputs:

  • explain row counts, scanned limits, missing data, and assumptions
  • distinguish measured facts from inferred interpretation
  • use Spreadsheet.create_spreadsheet_workbook when the user asks for Excel, XLSX, a tracker, a table package, or a reusable analysis workbook
  • include formulas, source columns, summary rows, and chart-ready tables when creating a workbook

Do not invent missing values. If a column is ambiguous, state the interpretation used.