Paper Harbor

What it does

Paper Harbor automates literature discovery and metadata collection for Zotero. It guides the agent through logged-in browser searches on ScienceDirect or CNKI, screens results by keywords, publication date, and impact factor rules, and writes screened metadata into CSVs and (when available) imports metadata-only items into a user-specified Zotero collection. The skill explicitly forbids downloading full text or bypassing paywalls and includes a first-use checklist for Zotero and browser setup.

When to use it

Use this skill when a user requests curated literature searches (by keywords, year range, impact-factor filters, and target counts) and wants clean, traceable outputs: candidate lists, address tables, priority CSVs, and Zotero import lists. It's ideal for literature reviews, project reading lists, and reproducible sourcing workflows.

What's included

• Scripts: references to helper scripts and a scripts/ workflow (doctor checks, browser port helpers) are documented though not bundled in every repo snapshot
• References: detailed procedural guidance for safe scraping, Zotero doctor checks, and CSV output scaffolding
• Instructions: step-by-step prompts, login port checks, and non-overrideable safety rules (no CAPTCHA solving, no paywall bypasses).

Compatible agents

Best used by agents capable of orchestrating browser automation and local integrations (agents with browser-control and local Zotero access). Works with assistants that can open ports, run local scripts, and interact with the user for login confirmations.