/empirical-ingest

Extract variables, datasets, and models from empirical papers into wiki pages.

77|16|Updated May 9, 2026
One-click install
npx skills add https://github.com/Lambenthan/empiricalwiki --skill empirical-ingest
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: /empirical-ingest
Source: https://github.com/Lambenthan/empiricalwiki/tree/main/.claude/skills/empirical-ingest
Command: npx skills add https://github.com/Lambenthan/empiricalwiki --skill empirical-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the manual, error-prone work of turning an empirical paper into structured, reusable research components by extracting variables, datasets, models, mechanisms, identification, robustness, and heterogeneity into a consistent wiki.

Core Features & Use Cases

  • End-to-end paper ingestion: Converts a local PDF/TEX (or a pre-prepared source) into wiki pages for the full empirical workflow, not just a summary.
  • Evidence-grounded extraction: Prioritizes extracting operational details (e.g., variable construction, identification strategy, robustness batteries) and avoids inventing unsupported facts by marking unreported items.
  • Graph-enabled knowledge linking: Generates wiki/graph/edges.jsonl to connect papers to variables, datasets, models, and key research relations with confidence and evidence.
  • Use case: When you read a new accounting/finance/econ paper that operationalizes the same construct differently, you can ingest it so the new variant lands alongside prior variants in the corresponding variable pages.

Quick Start

Ask the skill to ingest a local PDF into the empirical wiki with a topic hint, for example: empirical-ingest "<local-pdf-or-tex-path>" --topic "耐心资本与 ESG".

Frequently Asked Questions about /empirical-ingest

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

FAQPage Schema
How do I extract variables and identification strategies from empirical research papers into a structured wiki?

You can extract variables, datasets, models, and identification strategies from empirical papers into a structured wiki by ingesting local PDF or TEX files using template-based page generation, ensuring evidence-grounded extraction without fabrication.

What is the best way to build a reproducible research asset library from finance and economics PDFs?

The best way to build a reproducible research asset library from finance and economics PDFs is to ingest the full empirical workflow, converting local sources into persistent wiki pages for variables, robustness, heterogeneity, and graph links.

Can I generate a knowledge graph linking papers to datasets and models from local TEX files?

Yes, you can generate a knowledge graph linking papers to datasets and models from local TEX files by creating graph edges via the repository's indices, producing a jsonl file that connects papers to variables with confidence and evidence.

Does the paper ingestion process mark unreported empirical details or does it invent missing facts?

The paper ingestion process does not invent missing facts; it prioritizes evidence-grounded extraction of operational details and explicitly marks unreported items to avoid fabrication within the empirical wiki.

How do I ingest a new accounting paper that operationalizes a construct differently into an existing empirical wiki?

To ingest a new accounting paper with a different construct operationalization, you provide the local file path and a topic hint, allowing the new variant to land alongside prior variants in the corresponding variable pages.

When do I need to use empirical paper ingestion for a Stata pipeline?

You need to use empirical paper ingestion for a Stata pipeline when you require structured, evidence-grounded extraction of mechanisms, hypotheses, and robustness batteries from local PDFs to build a reproducible research asset library.