skills.rest
skaile-ai
skaile-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

knowledge-paper-research

Extract structured knowledge from scientific papers and generate research folders.

Updated Mar 28, 2026
Search Tags:#markdown#web-research#knowledge-extraction#docling#research-pipeline#paper-analysis#author-profiles
One-click install
npx skills add https://github.com/skaile-ai/ai-assets --skill knowledge-paper-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-paper-research
Source: https://github.com/skaile-ai/ai-assets/tree/main/knowledge-research/skills/knowledge-paper-research
Command: npx skills add https://github.com/skaile-ai/ai-assets --skill knowledge-paper-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires typer, rich, httpx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This pipeline turns a scientific paper into a structured knowledge package by extracting bibliographic metadata, creating a metadata file, and generating thematic research outputs for deeper understanding and contextualization.

Core Features & Use Cases

  • Structured extraction: parses title, authors, abstract, year, venue, DOI, sections, and references from PDFs or Markdown sources.
  • Research packaging: creates a co-located metadata file next to the paper and a dedicated <stem>_research/ folder containing four thematic files plus author profiles.
  • Web-context enrichment: performs web searches across multiple dimensions to build external context and related work for thorough understanding.
  • Use Case: ideal for preparing research briefs, literature reviews, or enrichment of a manuscript with external context.

Quick Start

Provide the path to a paper (PDF or Markdown) to generate a metadata file next to the paper and a dedicated research folder with four thematic files plus per-author profiles.

Frequently Asked Questions about knowledge-paper-research

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

FAQPage Schema
How do I extract structured metadata and references from a scientific paper PDF?▼

To extract structured metadata from a scientific paper PDF, this pipeline uses docling to convert PDFs to Markdown, then parses title, authors, abstract, year, venue, DOI, sections, and references into a co-located metadata file.

What is the best way to enrich paper analysis with external web context?▼

Enriching paper analysis with external web context requires a running web-search tool like SearXNG. This pipeline queries web sources across multiple dimensions to build external context and related work for thorough understanding.

How do I generate per-author profiles and thematic research files from Markdown papers?▼

Generating per-author profiles and thematic research files from Markdown papers involves running a full structured-knowledge extraction pipeline, which creates a dedicated research folder containing four thematic files alongside individual author profiles.

Do I need SearXNG to run the research pipeline for literature reviews?▼

Yes, you need SearXNG or an equivalent web-search tool configured via SEARXNG_URL to run the research pipeline, as it performs the web searches necessary to build external context for literature reviews and research briefs.

Can I use this pipeline to prepare a research briefing from an existing Markdown document?▼

Yes, you can use this pipeline to prepare a research briefing from a Markdown document by providing its path, which triggers structured-knowledge extraction and web-research packaging for deep understanding and contextualization.

What limitations exist when converting PDFs to Markdown for knowledge extraction?▼

A key limitation when converting PDFs to Markdown for knowledge extraction is the dependency on docling for accurate conversion, meaning poorly formatted PDFs may result in incomplete section parsing or missing reference data.

Related Skills

Explore More Education & Research Skills→
devskaledevskale
1

searxng-search

Query a SearXNG instance via Python HTTP requests with filters.

Community
Intermediate
zm2231zm2231

literature-review

Generate PRISMA-compliant systematic literature reviews with thematic analyses and citation networks.

Community
Advanced
Tommy-ywTommy-yw
539

ocr-and-documents

Convert PDFs and scanned documents into editable text using OCR.

Community
Intermediate
xukrutdonutxukrutdonut

zotero

Manage Zotero libraries via REST API for search, export, and PDF handling.

Community
Intermediate