serper-scholar▌
fanzhidongyzby/openclaw-serper · updated Apr 8, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
基于 Google Scholar API 的学术文献搜索工具,提供学术论文、研究报告、技术文献的专业搜索能力。
Google Scholar Search Tool
基于 Google Scholar API 的学术文献搜索工具,提供学术论文、研究报告、技术文献的专业搜索能力。
When to Activate
当用户提到以下内容时自动激活:
学术搜索关键词
- "论文"、"学术"、"文献"、"研究"
- "搜索论文"、"查找文献"、"学术研究"
- "谷歌学术"、"Scholar"
特定场景
- 需要查找学术论文或研究报告
- 需要了解某领域的学术进展
- 需要查找特定作者的作品
- 需要获取引用信息和发表刊物
- 需要研究技术领域的理论依据
示例问题
- "帮我搜索关于机器学习的论文"
- "查找一下深度学习在 NLP 中的应用"
- "研究一下 Transformer 架构的学术论文"
- "找一些关于大模型训练方法的文献"
- "搜索一下 Attention mechanism 的相关论文"
Tools
serper_scholar
用途: 执行学术文献搜索,返回论文详细信息
参数:
query(必选,string):搜索关键词num(可选,number):返回结果数量,默认 10,最大 20gl(可选,string):国家代码,默认 cn- 推荐值: cn(中国)、us(美国)、uk(英国)
hl(可选,string):语言代码,默认 zh-CN- 推荐值: zh-CN(简体中文)、en(英文)
返回字段:
title:论文标题url:论文链接snippet:摘要type:文献类型(PDF、HTML 等)year:发表年份authors:作者列表publication:发表刊物/会议citationCount:引用次数
Best Practices
1. 搜索技巧
使用专业术语和技术关键词:
示例:
- ✅ "Attention mechanism neural machine translation"
- ✅ "Transformer large language models"
- ✅ "Reinforcement learning robotics"
- ❌ "机器学习"(太宽泛,结果太多)
2. 添加领域限定
明确研究领域和方法:
示例:
- ✅ "BERT semantic analysis NLP"
- ✅ "CNN image classification computer vision"
- ✅ "GPT text generation natural language"
- ✅ "Q-learning reinforcement learning agent"
3. 时间范围搜索
关注最新研究进展:
示例:
- ✅ "Large language models 2024 2025"
- ✅ "Transformer architecture recent advances"
- ✅ "Diffusion models 2023 2024"
4. 作者和机构搜索
查找特定研究者或机构的工作:
示例:
- ✅ "Geoffrey Hinton deep learning"
- ✅ "Yann LeCun CNN papers"
- ✅ "Andrew Ng machine learning"
- ✅ "OpenAI research papers"
5. 论文类型筛选
关注特定类型的文献:
示例:
- ✅ "Survey deep learning"
- ✅ "Review transformer models"
- ✅ "Tutorial reinforcement learning"
- ✅ "Benchmark NLP models"
6. 结果数量选择
根据需求调整:
- 快速浏览:
num=5(核心文献) - 全面了解:
num=10(主流研究) - 深度调研:
num=20(全面覆盖)
7. 引用信息分析
关注高引用论文和经典文献:
关注点:
- 引用次数:
citationCount高的论文通常是领域经典 - 发表年份:较新的论文代表最新进展
- 发表刊物:顶级会议(NeurIPS、ICML、ACL)质量高
Example Scenarios
场景 1:技术调研
用户提问: "研究一下 Transformer 架构的论文"
AI 行为:
// 搜索核心论文
serper_scholar({
query: "Transformer architecture attention is all you need",
num: 5
})
// 搜索后续研究
serper_scholar({
query: "BERT transformer NLP 2018 2019",
num: 8
})
回复示例:
核心论文:
1. **Attention Is All You Need** (2017)
- 作者:Vaswani et al.
- 引用:100,000+
- 📄 [PDF]
后续研究:
2. **BERT: Pre-training of Deep Bidirectional Transformers** (2019)
- 作者:Devlin et al.
- 引用:80,000+
- 发表:NAACL 2019
3. **Improving Language Understanding with Generative Pre-Training** (2018)
- 作者:Radford et al. (OpenAI)
- 引用:50,000+
场景 2:领域综述
用户提问: "找一些关于强化学习的综述论文"
AI 行为:
serper_scholar({
query: "Survey review reinforcement learning",
num: 8
})
回复示例:
强化学习综述论文:
1. **Reinforcement Learning: A Survey** (2021)
- 引用:5,000+
- 类型:综述
2. **Deep Reinforcement Learning: An Overview** (2020)
- 引用:8,000+
- 类型:综述
3. **Recent Advances in Deep Reinforcement Learning** (2022)
- 引用:2,000+
- 类型:综述
场景 3:作者研究
用户提问: "查找 Geoffrey Hinton 的深度学习论文"
AI 行为:
serper_scholar({
query: "Geoffrey Hinton deep learning backpropagation",
num: 10
})
回复示例:
Geoffrey Hinton 的经典论文:
1. **Deep Learning** (2015)
- 合作:LeCun, Bengio
- 发表:Nature
- 引用:50,000+
2. **Backpropagation Applied to Handwritten Zip Code Recognition** (1989)
- 引用:10,000+
3. **Reducing the Dimensionality of Data with Neural Networks** (2006)
- 引用:30,000+
场景 4:最新进展
用户提问: "2024-2025 年大模型有什么新进展"
AI 行为:
serper_scholar({
query: "Large language models 2024 2025 advances",
num: 10
})
回复示例:
2024-2025 大模型研究进展:
1. **Scaling Laws for Neural Language Models** (2024)
- 持续探索模型规模与性能关系
2. **Instruction Tuning for Large Language Models** (2024)
- 指令微调方法改进
3. **Chain-of-Thought Prompting** (2024)
- 推理链提示技术
场景 5:跨学科搜索
用户提问: "搜索机器学习在医疗诊断中的应用论文"
AI 行为:
serper_scholar({
query: "Machine learning medical diagnosis healthcare",
num: 8
})
回复示例:
医疗诊断中的机器学习:
1. **Deep Learning for Medical Image Analysis** (2021)
- 引用:8,000+
- 应用:影像诊断
2. **Machine Learning in Clinical Diagnosis** (2022)
- 引用:3,000+
- 应用:辅助诊断
3. **AI in Healthcare: A Survey** (2023)
- 引用:2,000+
- 类型:综述
Limitations
- 搜索结果来源: Google Scholar,可能受地区影响
- 访问限制: 某些论文需要订阅或付费访问
- 结果数量: 最多 20 条
- 更新延迟: 最新论文可能需要一段时间才会被收录
- 语言偏好: 英文论文数量远多于中文
Configuration
环境变量配置
编辑 ~/.openclaw/gateway.env:
SERPER_API_KEY=your-api-key-here
获取 API Key
访问 https://serper.dev/ 注册并获取 API Key。
免费额度:每月 2,500 次调用(Web 和 Scholar 共享)。
Related Tools
- serper_search: 普通网页搜索
- web_fetch: 获取单个网页的详细内容
Tips
- 混合使用: 先用 serper_search 了解概念,再用 serper_scholar 深入研究
- 引用优先: 优先阅读高引用论文(通常是领域经典)
- 关注年份: 平衡经典文献和最新研究
- 追踪作者: 找到重要作者后,搜索其全部作品
- PDF 访问: 尝试访问论文页面,寻找免费版本
Version History
- v1.0 (2026-02-06):初始版本,基础学术搜索功能
- 支持 Google Scholar API
- 提供论文详细信息(作者、年份、引用等)
- 集成 OpenClaw Skill 系统
💡 提示: 学术搜索时,尽量使用英文关键词,英文论文数量和质量通常更高。
How to use serper-scholar on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add serper-scholar
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches serper-scholar from GitHub repository fanzhidongyzby/openclaw-serper and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate serper-scholar. Access the skill through slash commands (e.g., /serper-scholar) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
User Story & Requirements Generation
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Competitive Analysis
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Roadmap Prioritization
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
Make data-driven prioritization decisions faster
Stakeholder Communication
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client
- ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
- ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
- ›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Installation Steps
- 1.Install product management skill
- 2.Start with user story generation for known feature
- 3.Progress to competitive analysis: research 2-3 competitors
- 4.Use for roadmap prioritization: apply RICE/ICE scoring
- 5.Draft stakeholder communications and refine based on feedback
- 6.Build template library for recurring PM tasks
- 7.Share effective prompts with product team
Common Pitfalls
- ⚠Not validating competitive research—verify facts before sharing
- ⚠Accepting user stories without involving engineering team
- ⚠Over-relying on frameworks without qualitative judgment
- ⚠Not customizing outputs to company culture and communication style
- ⚠Skipping stakeholder validation of generated requirements
Best Practices▌
✓ Do
- +Validate research and competitive analysis with real data
- +Collaborate with engineering when generating technical requirements
- +Customize frameworks and templates to your company context
- +Use skill for first drafts, refine with stakeholder input
- +Document successful prompt patterns for PM tasks
- +Combine AI efficiency with human judgment and intuition
✗ Don't
- −Don't publish competitive analysis without fact-checking
- −Don't finalize user stories without engineering review
- −Don't make prioritization decisions solely on AI scoring
- −Don't skip customer validation of generated requirements
- −Don't ignore company-specific context and culture
💡 Pro Tips
- ★Provide context: company goals, constraints, customer feedback
- ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
- ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
- ★Use skill for 70% generation + 30% customization to company needs
When to Use This▌
✓ Use When
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid When
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path▌
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.7★★★★★31 reviews- ★★★★★Ishan Verma· Dec 24, 2024
We added serper-scholar from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Chaitanya Patil· Dec 16, 2024
Useful defaults in serper-scholar — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Kaira Patel· Dec 4, 2024
serper-scholar fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Zara Nasser· Nov 23, 2024
Registry listing for serper-scholar matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Chen Verma· Nov 19, 2024
Solid pick for teams standardizing on skills: serper-scholar is focused, and the summary matches what you get after install.
- ★★★★★Layla Kim· Nov 15, 2024
serper-scholar reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Piyush G· Nov 7, 2024
serper-scholar is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Shikha Mishra· Oct 26, 2024
Keeps context tight: serper-scholar is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Zara Wang· Oct 14, 2024
serper-scholar reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Chen Dixit· Oct 10, 2024
serper-scholar has been reliable in day-to-day use. Documentation quality is above average for community skills.
showing 1-10 of 31