bigquery-seeds

Creates BigQuery-backed seed datasets from publicly queryable tables for forecasting and training.

57|6|Updated Jan 16, 2026
One-click install
npx skills add https://github.com/lightning-rod-labs/lightningrod-python-sdk --skill bigquery-seeds
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bigquery-seeds
Source: https://github.com/lightning-rod-labs/lightningrod-python-sdk/tree/main/skills/bigquery-seeds
Command: npx skills add https://github.com/lightning-rod-labs/lightningrod-python-sdk --skill bigquery-seeds

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

BigQuery-seeds helps you turn publicly queryable BigQuery tables into labeled training seeds without manual dataset wrangling.

Core Features & Use Cases

  • Seed generation from BigQuery: Run SQL against BigQuery to retrieve text plus a date field, then package rows as seeds for downstream labeling.
  • Label-in-SQL pattern: Embed ground-truth fields (like scores or accepted answers) inside the seed text so a question/label generator can extract both from the same result.
  • Schema inspection & safe dataset selection: Validate table schemas and restrict sourcing to publicly queryable datasets (no private tables, no paid commercial datasets).

Use case: generate hundreds of forecasting question candidates from Hacker News stories by selecting title, score, and text while attaching timestamps for time-aware labeling.

Quick Start

Ask an AI to generate BigQuery seed rows from a public table by providing a query, the text column, and the date column.

Frequently Asked Questions about bigquery-seeds

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

FAQPage Schema
How do I generate training seeds from public BigQuery datasets?

To generate training seeds from BigQuery, you provide a valid SQL query, specify the text and date columns, and the tool packages the retrieved rows into seeds for downstream question-and-label extraction.

What is the label-in-SQL pattern for seed generation?

The label-in-SQL pattern embeds ground-truth fields, such as scores or accepted answers, directly inside the seed text so a generator can extract both the question and label from the same query result.

Can I use BigQuery seed generation with private or commercial paywalled datasets?

No, BigQuery seed generation restricts sourcing to publicly queryable datasets and explicitly excludes private tables and paid commercial datasets to ensure safe and compliant data selection.

How do I source text and timestamps from BigQuery for forecasting pipelines?

You source text and timestamps by running a SQL query against public BigQuery tables, explicitly mapping your text and date columns to package the results into time-aware forecasting seeds.

Does BigQuery seed generation support limiting the number of rows retrieved?

Yes, you can apply an optional max-row limit during seed generation to control iteration size and restrict the number of rows retrieved from the public BigQuery tables.

What's the best way to validate table schemas before sourcing seeds from BigQuery?

Schema inspection is built into the seed generation process, allowing you to validate table schemas and ensure safe dataset selection before retrieving text and date fields from public BigQuery tables.