MCP App StoreMCP App Store
from paper-harbor-skill17
An automated literature capture workflow that searches ScienceDirect or CNKI, screens results by user rules, and saves metadata-only records into Zotero while r
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.
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.
scripts/ workflow (doctor checks, browser port helpers) are documented though not bundled in every repo snapshotBest 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.
Paper Harbor is a literature search and Zotero metadata import workflow for ScienceDirect and CNKI. It has strong safety rules prohibiting full-text download, paywall bypass, and CAPTCHA circumvention. Scripts are well-structured but require DrissionPage (not installed) and specific CLI arguments to run. Two main runner scripts (sciencedirect_drission_run.py, cnki_drission_run.py) failed on missing DrissionPage import. Scaffold and bridge scripts work but need arguments. The skill is niche but well-designed for its target audience of academic researchers.
DrissionPageThis skill has exceptionally strong safety rules explicitly prohibiting paywall bypass, CAPTCHA solving, full-text downloading, and pirate mirror usage. The SKILL.md is comprehensive (perhaps too long — could benefit from references/ directory for site-specific details). Architecture is sound but the SKILL.md could be more concise with progressive disclosure. DrissionPage dependency is a significant barrier to running scripts out of the box.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.
Writing Implementation Plans
Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
AI News Daily
Generate a structured, bilingual daily briefing of the latest AI industry news, model updates, papers, and open-source tools with in-depth technical analysis an
ToolUniverse Gateway
Unified agent gateway to 1000+ scientific tools (bioinformatics, drug discovery, genomics) via Harvard's ToolUniverse, returning JSON for downstream workflows.
Research Information Lookup
Find and synthesize current research and academic papers with automatic backend routing (Parallel Chat API or Perplexity) and structured citations.
arXiv Paper Search & Download
Search arXiv, fetch paper metadata, download PDFs, and produce concise summaries for academic papers (ID or query).