skills.rest
LightconeResearch
LightconeResearchOFFICIAL
Explore all skills by this author →
GitHub

paper-extraction

Convert an arXiv ID or DOI into a standardized paper directory with index.json and astra.yaml.

18|2|Updated Feb 15, 2026
Search Tags:#arxiv#doi#astra#paper ingestion#citation resolution#latex extraction#structured indexing
One-click install
npx skills add https://github.com/LightconeResearch/lightcone-cli --skill paper-extraction-lightconeresearch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: paper-extraction
Source: https://github.com/LightconeResearch/lightcone-cli/tree/main/claude/lightcone/skills/paper-extraction
Command: npx skills add https://github.com/LightconeResearch/lightcone-cli --skill paper-extraction-lightconeresearch

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

paper-extraction removes the burden of manually downloading a paper and re-parsing PDFs/LaTeX to find figures, tables, section structure, and citation metadata, by producing a standardized directory with both structural and semantic surfaces.

Core Features & Use Cases

  • Standardized paper substrate: Converts an arXiv ID or DOI into a predictable work/reference/ layout containing the paper PDF plus either arXiv LaTeX source artifacts (primary) or a Docling-derived fallback surface.
  • Structural index for fast navigation: Emits work/reference/index.json with figures, tables (as per-table .tex files on the LaTeX path), section outline with line numbers, and a citations map including resolved DOIs and full citation text when available.
  • ASTRA-shaped semantic representation: Writes work/reference/astra.yaml as a valid ASTRA artifact stub, ready for follow-on findings population with evidence-anchored quotes.
  • Use Case: Prepare a reliable, shareable reading surface before deeper analysis, so other workflows can consume figures/tables/citations without re-grepping LaTeX or re-wrangling PDFs.

Quick Start

Ask the agent to run paper-extraction for a paper by providing its arXiv ID or DOI, so you get a ready-to-consume work/reference/ directory with index.json and astra.yaml.

Frequently Asked Questions about paper-extraction

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

FAQPage Schema
How do I extract figures and section structure from an arXiv paper?▼

You can extract figures and section structure by providing an arXiv ID or DOI, which generates a standardized directory with LaTeX source artifacts and an index.json file mapping line numbers to sections.

What is the best way to resolve citation metadata for research papers automatically?▼

Automatically resolving citation metadata involves translating a DOI into a standardized local representation, caching DOI resolution results, and emitting a citations map with fully resolved DOIs and citation text in an index.json file.

Can I extract tables from arXiv LaTeX source files into separate files?▼

Yes, extracting tables from arXiv LaTeX source files creates per-table .tex files within a standardized work/reference directory, enabling downstream workflows to consume individual table artifacts without re-grepping the original LaTeX.

Does paper ingestion work with DOI resolution when arXiv LaTeX is unavailable?▼

Paper ingestion handles cases where arXiv LaTeX is unavailable by falling back to a Docling-derived surface, while still performing idempotent extraction and caching DOI resolution results to maintain a consistent directory shape.

Why do I need a standardized directory layout for research paper ingestion?▼

A standardized directory layout is needed for research paper ingestion so downstream workflows can reliably consume figures, tables, and citations without manually re-parsing PDFs or re-wrangling LaTeX source files.

How do I prepare an ASTRA artifact stub from a research paper?▼

To prepare an ASTRA artifact stub from a research paper, the ingestion process writes a valid astra.yaml file into the work/reference directory, ready for follow-on findings population with evidence-anchored quotes.

Related Skills

Explore More Education & Research Skills→
tangshunputangshunpu
7

arxiv-downloader

Download and extract LaTeX sources from arXiv papers using curl or wget.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
jaminitachijaminitachi
1

paper-review

Extract methodology, findings, and limitations from academic papers into a knowledge graph.

Community
Advanced
LingrongyeLingrongye
1

paper-figure

Generate publication-ready figures and LaTeX tables from JSON/CSV data.

Community
Advanced