skills.rest
lightning-rod-labs
lightning-rod-labsOFFICIAL
Explore all skills by this author →
Website𝕏@lightningrodaiGitHub

tabular-examples

Convert tabular data into forecasting training samples with labels and temporal metadata.

57|6|Updated Jan 16, 2026
Search Tags:#tabular data#forecasting dataset#label generation#question templating#news context#time-series splitting#data leakage checks
One-click install
npx skills add https://github.com/lightning-rod-labs/lightningrod-python-sdk --skill tabular-examples
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tabular-examples
Source: https://github.com/lightning-rod-labs/lightningrod-python-sdk/tree/main/skills/tabular-examples
Command: npx skills add https://github.com/lightning-rod-labs/lightningrod-python-sdk --skill tabular-examples

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you map messy structured/tabular data into high-quality LLM training samples with correct labels, prediction dates, and resolution criteria.

Core Features & Use Cases

  • Map rows to Sample fields: Convert CSV/BigQuery/API outputs into Sample() components like question_text, label, prediction_date, and resolution metadata.
  • Compute labels from outcomes: Define outcomes (e.g., shock vs no shock) from time-series or derived columns, while avoiding leakage.
  • Generate questions and add real-world context: Use TemplateQuestionGenerator for consistent question text and optionally NewsContextGenerator plus a renderer to enrich prompts.
  • Production-oriented walkthrough: Includes a supply-chain shock detection example that you can adapt to other tabular forecasting setups (including time splits for train/test).

Quick Start

Ask the AI to adapt the supply chain shock detection pipeline by mapping your tabular fields into create_sample(), generating questions with TemplateQuestionGenerator, and (optionally) enriching prompts with NewsContextGenerator for your forecasting dataset.

Frequently Asked Questions about tabular-examples

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

FAQPage Schema
How do I convert tabular rows into forecast-ready datasets for LLM training?▼

To convert tabular rows into forecast-ready datasets, map structured CSV or BigQuery outputs into Sample fields like question_text and label, then generate prompts using TemplateQuestionGenerator while enforcing temporal metadata to prevent label leakage.

How do I prevent label leakage when computing outcomes from time-series data?▼

Prevent label leakage in time-series data by enforcing correct temporal metadata, ensuring the prediction_date strictly precedes the resolution date, and applying proper time-series splitting between training and testing samples.

Can I add real-world news context to generated forecasting questions?▼

Yes, you can add real-world news context to forecasting questions by integrating NewsContextGenerator into the SDK pipeline workflow alongside a renderer to enrich the prompt with external verification sources.

What is the best way to generate consistent question text for tabular forecasting samples?▼

The best way to generate consistent question text for tabular forecasting samples is using TemplateQuestionGenerator within an SDK pipeline renderer workflow to standardize prompts across mapped rows.

Does this approach work with BigQuery outputs and CSV files for supply chain forecasting?▼

Yes, this approach works with BigQuery outputs and CSV files for supply chain forecasting by mapping tabular fields into create_sample components and adapting the included supply-chain shock detection pipeline.

Related Skills

Explore More Data & Analytics Skills→
HeshamFSHeshamFS
61

post-processing

Extract fields, analyze time series, and generate reports from simulation output data.

Community
Advanced
pmcdowallpmcdowall

fine-tuning-with-trl

Align large language models via reinforcement learning and preference-based fine-tuning workflows.

Community
Advanced
rodolfodpkrodolfodpk
1

crablet-diagram-advisor

Guide creation and review of event-model diagrams with actors, lanes, and assignments.

Community
Intermediate
vasilyu1983vasilyu1983
73

ai-ml-timeseries

Forecast time series data with LightGBM, Transformers, and SHAP.

Community
Advanced