foundations_skill

This skill helps you master data analytics fundamentals, spreadsheet techniques, and data collection methods to improve data-driven decision making.

Python

1

GitHub Stars

4

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill pluginagentmarketplace/custom-plugin-data-analyst --skill foundations

data-collection.md6.1 KB
excel-fundamentals.md4.5 KB
google-sheets.md4.6 KB
SKILL.md2.2 KB

Overview

This skill teaches core data analytics concepts, spreadsheet fundamentals, and practical data collection techniques for everyday analysis. It focuses on data types, quality dimensions, Excel/Google Sheets proficiency, and basic methods for acquiring data from surveys, APIs, and web sources. The goal is to equip practitioners with repeatable workflows for cleaning, summarizing, and preparing data for analysis.

How this skill works

The skill inspects common data scenarios and provides concrete steps to identify data types, assess data quality, and apply cleaning or transformation patterns in spreadsheets. It demonstrates formula strategies, pivot table workflows, and collaboration features in Google Sheets, plus basic scripts and queries for pulling data from APIs, web pages, and databases. Error-handling guidance covers formula fixes, type conversions, missing data approaches, and performance workarounds.

When to use it

Preparing raw datasets for analysis or reporting
Designing and running surveys or extracting data from APIs
Cleaning and transforming data inside Excel or Google Sheets
Summarizing large tables with pivot tables and formulas
Assessing data quality before modeling or visualization

Best practices

Start by classifying variables (quantitative vs qualitative) and expected formats
Document data sources, collection dates, and processing steps for reproducibility
Prefer explicit data-type conversions to avoid silent errors
Use pivot tables and grouped summaries before building models
Sample large datasets to prototype formulas and optimize performance

Example use cases

Build a clean customer transaction table from exported CSVs and an API feed
Design a survey, collect responses, and prepare results for pivot-table analysis
Automate regular pulls from a web API into Google Sheets and flag anomalies
Scrape basic tabular data from a public website and normalize fields for analysis
Troubleshoot formula errors and resolve type mismatches in a shared spreadsheet

FAQ

Use Excel for heavy computation and advanced formulas; choose Google Sheets for real-time collaboration and lightweight automation. Start in Sheets for shared workflows and move to Excel if you hit performance limits.

How do I handle missing or inconsistent data?

First identify patterns of missingness, then apply simple imputation, filtering, or flagging depending on the analysis. Always record the method used and test sensitivity of results to those choices.