paper-summary

Generate deterministic Markdown summaries from PDFs with evidence anchors.

11|1|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/jimezsa/opencolab --skill paper-summary-jimezsa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-summary
Source: https://github.com/jimezsa/opencolab/tree/main/projects/SKILLS/paper-summary
Command: npx skills add https://github.com/jimezsa/opencolab --skill paper-summary-jimezsa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Automatically generate deterministic, schema-conformant Markdown summaries from research PDFs to accelerate literature review and indexing.

Core Features & Use Cases

  • Deterministic, schema-conformant summaries produced from PDFs using Gemini.
  • Supports optional metadata integration and batch processing for multiple papers.
  • Keeps evidence anchors (figures, captions, tables) from the source PDFs to ensure traceability.

Quick Start

Provide a PDF path or a directory of PDFs and run the paper-summary workflow to generate schema-conformant Markdown summaries.

Frequently Asked Questions about paper-summary

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

FAQPage Schema
How do I generate markdown summaries from PDFs for a literature review?

Generating markdown summaries from PDFs involves providing a single file or directory path to the workflow. The tool reads the PDFs and outputs schema-conformant markdown summaries directly next to the source files.

Can I batch process multiple research PDFs to create markdown summaries?

Yes, you can batch process research PDFs by providing a directory path. The workflow generates deterministic markdown summaries for each paper to streamline literature indexing.

Does the PDF summarization workflow preserve evidence anchors from the source document?

Yes, the PDF summarization workflow preserves evidence anchors from the source document. It retains figures, captions, and tables from the source PDFs to ensure traceability during literature review.

Do I need Python and the google-genai client to generate markdown paper summaries?

Yes, generating markdown paper summaries requires Python 3 and the google-genai client. These dependencies are necessary to run the workflow and process the PDF files into deterministic markdown.

Can I use metadata JSONs to enrich markdown summaries generated from PDFs?

Yes, you can use metadata JSONs to enrich markdown summaries generated from PDFs. The workflow reads optional metadata files to integrate additional context into the final markdown output.

What is the best way to convert research PDFs to deterministic markdown?

The best way to convert research PDFs to deterministic markdown is using a schema-conformant workflow that leverages Gemini. This approach ensures consistent summaries while keeping source evidence anchors intact.