LaunchKit · 2026
Back to Skills

A Research Assistant workflow skill with four core commands: search papers, download PDFs, analyze content.

2
894 downloads
by @cxlhyx

Setup & Installation

openclaw skills install @cxlhyx/hxxra

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install hxxra

Version History

v1.2.0Mar 11, 2026 - Version note by skill developer:

**v1.2.0 · 2026/3/8** - Added `report` command to generate comprehensive Markdown reports from all `analysis.json` files - Report includes keyword statistics, overview table, and detailed content for each paper - Supports sorting by year (default), title, or author - Generates clean, readable Markdown format with tables, headers, and structured content - Updated documentation to include the new report command in workflows and examples

What This Skill Does

hxxra is a research assistant that runs five commands: search papers on Google Scholar or arXiv, download PDFs, analyze content with an LLM, generate Markdown reports, and save references to Zotero. It communicates via stdin/stdout JSON and is invoked through a Python script.

Combining search, download, LLM analysis, and Zotero export in a single pipeline eliminates the need to switch between separate tools for each step of a literature review.

When to use it

  • Searching arXiv for recent papers on a specific ML topic
  • Downloading and analyzing a batch of PDFs from search results
  • Generating a structured Markdown report sorted by publication year
  • Saving curated paper sets to a Zotero collection for citation management
  • Running a full literature review pipeline from search to report in one session

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: find and analyze recent papers on graph neural networks, then save them to Zotero

AGENT
  1. 1Run search command with query 'graph neural networks', source arxiv, limit 10, output to searches/gnn_arxiv.json
  2. 2Run download command pointing to gnn_arxiv.json, saving PDFs to papers/
  3. 3Run analyze command on the papers/ directory to produce analysis.json files per paper
  4. 4Run report command on papers/ to generate a Markdown summary sorted by year
  5. 5Run save command with gnn_arxiv.json pointing to a Zotero collection named 'GNN Papers'
OUTPUT

Downloaded PDFs with per-paper analysis.json files, a compiled report.md, and all papers saved to the specified Zotero collection

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

OpenAI API key (or compatible LLM API key) for the analyze commandZotero API key from zotero.org/settings/keys/newZotero user ID found on the Zotero API keys settings page