Use Case
Literature Reviewer Skill is a powerful AI agent skill that extends your assistant with new capabilities. Conduct a systematic literature review (Literature Survey) in both Chinese and English based on the paper topics provided by the user. It adopts an 8-stage workflow and supports mainstream databases such as CNKI, Web of Science, and ScienceDirect. It does not require API configuration and automatically obtains literature information through the browser. Output Markdown text containing GB/T 7714-2015 citations, titles, and abstracts... This guide walks you through installing Literature Reviewer Skill, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Literature Reviewer Skill: npx clawhub@latest --dir ~/.claude/skills install literature-reviewer-skill
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to data & analytics to trigger Literature Reviewer Skill
Review the output and refine your prompt for better results
Combine Literature Reviewer Skill with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Literature Reviewer Skill
Help me get started with Literature Reviewer Skill
What can Literature Reviewer Skill do for my data & analytics workflow?
Show me an example of using Literature Reviewer Skill
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install literature-reviewer-skillOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install literature-reviewer-skillβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/literature-reviewer-skill/π‘Extract and place the folder at the path above, then restart your agent.