paper-sync

Diagnose paper pool health, enrich metadata, download PDFs, and annotate results.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Biajin-PKU/research-harness --skill paper-sync
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-sync
Source: https://github.com/Biajin-PKU/research-harness/tree/main/codex-skills/paper-sync
Command: npx skills add https://github.com/Biajin-PKU/research-harness --skill paper-sync

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill closes the gaps in a topic's paper pool by diagnosing health, enriching metadata, downloading PDFs, and annotating results to enable reliable downstream analysis (gap analysis, claim extraction, and write-up).

Core Features & Use Cases

  • Inspect pool health and classify papers by status (complete, needs download, needs enrichment, noise candidates, unreachable).
  • Enrich metadata, download PDFs, annotate, and generate a prioritized missing-content report.
  • Filter out low-relevance noise before downloading and support manual review when needed.

Quick Start

Provide a topic name or ID and run the /paper-sync command to synchronize and annotate the topic's papers.

Frequently Asked Questions about paper-sync

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

FAQPage Schema
How do I automatically fetch missing metadata and download PDFs for a literature review?

To fetch missing metadata and download PDFs for a literature review, use paper-sync to diagnose pool health, enrich incomplete records, and acquire full texts automatically. It classifies papers by status and filters low-relevance noise before downloading.

What is the best way to filter low-relevance noise from a research paper pool before downloading?

Filtering low-relevance noise from a research paper pool requires diagnosing health and classifying entries as noise candidates. Paper-sync identifies these unreachable or irrelevant records and prevents unnecessary PDF downloads while supporting manual review.

Does paper-sync require integration with Research Harness tools to annotate results?

Yes, paper-sync requires integration with Research Harness tools like topic_show, paper_list, and paper_acquire to annotate results. It uses these commands to synchronize content, fetch metadata, and manage paper pool health effectively.

When should I run paper synchronization after citation tracing?

Run paper synchronization immediately after citation tracing or literature searches and before gap analysis. This ensures your topic pool has complete metadata and full-text coverage, enabling reliable downstream claim extraction and write-up.

How do I generate a prioritized missing-content report for my research topics?

Generate a prioritized missing-content report by diagnosing your topic pool health and classifying papers by status. Paper-sync inspects the pool, identifies unreachable or incomplete records, and outputs a prioritized report for manual review.