skills.rest
spm1001
spm1001COMMUNITY
Explore all skills by this author →
GitHub

mandoline

Transform raw survey data and CSV dumps into self-documenting BigQuery tables.

3|Updated Jan 14, 2026
Search Tags:#schema design#metadata#data transformation#data cleaning#survey data#bigquery
One-click install
npx skills add https://github.com/spm1001/trousse --skill mandoline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mandoline
Source: https://github.com/spm1001/trousse/tree/main/skills/mandoline
Command: npx skills add https://github.com/spm1001/trousse --skill mandoline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the transformation of raw, opaque survey data and CSV dumps into self-documenting, clean BigQuery tables, preventing LLM hallucinations and enabling direct analysis.

Core Features & Use Cases

  • Schema Design: Guides the creation of descriptive column names, appropriate data types, and decodes numeric codes into human-readable labels.
  • Data Cleaning: Handles filtering of junk rows, conversion of placeholder values to NULL, and snapshotting of fragile Sheets-linked data.
  • Metadata Enrichment: Writes teaching-style column descriptions, table descriptions, friendly names, and labels for enhanced discoverability and usability.
  • Automated Verification: Includes a suite of SQL checks to ensure data integrity and transformation accuracy.
  • Use Case: When presented with a raw survey export containing columns like S1, Q1r3, and coded responses, use Mandoline to create a BigQuery table where columns are named gender, action_physical_activity, and values are clearly labeled 'Male', 'Female', 'Yes', 'No', with rich descriptions explaining their meaning and usage.

Quick Start

Use the mandoline skill to transform the raw data in the 'raw_survey_data' table into a clean, analysis-ready table with proper descriptions and metadata.

Frequently Asked Questions about mandoline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transform raw survey data into analysis-ready BigQuery tables?▼

Transform raw survey data into analysis-ready BigQuery tables by applying automated schema design, data cleaning, and metadata enrichment to decode opaque columns and coded responses into self-documenting formats.

What is the best way to clean CSV dumps and decode numeric survey responses in BigQuery?▼

Cleaning CSV dumps and decoding numeric survey responses involves filtering junk rows, converting placeholders to NULL, and mapping coded values like 'S1' and 'Q1r3' into human-readable labels such as 'gender' and 'action_physical_activity'.

How do I add metadata and column descriptions to BigQuery tables for survey data?▼

Add metadata and column descriptions to BigQuery tables by writing teaching-style descriptions, friendly names, and labels, which enhances discoverability and prevents LLM hallucinations during direct analysis.

Do I need BigQuery client libraries and SQL to verify data transformation accuracy?▼

Yes, BigQuery client libraries and SQL are required to verify data transformation accuracy. The process includes running a suite of automated SQL checks to ensure data integrity after cleaning raw survey exports.

Can I snapshot fragile Google Sheets linked data before transforming it in BigQuery?▼

You can snapshot fragile Sheets-linked data during the data cleaning process to preserve its current state before converting placeholder values and applying schema design for analytical readiness.

Related Skills

Explore More Data & Analytics Skills→
wangx7wangx7

bigquery-basics

Manage BigQuery datasets, tables, and jobs via CLI, client libraries, and MCP servers.

Community
Intermediate
mozillamozilla
10

model-requirements

Gather BigQuery data model requirements and validate dependencies for bqetl queries.

Official
Advanced
data-flowersdata-flowers

ptah-data-flow

Convert CSV, PDF, and HTML data into Ptah-compatible datasets.

Official
Advanced
vruum-gtmvruum-gtm

csv-pipeline-fill

Normalize and validate CSV prospect lists for automated sales pipeline enrichment.

Official
Advanced