Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fanzhidongyzby/openclaw-serper --skill serper-scholargit clone --depth 1 https://github.com/fanzhidongyzby/openclaw-serperWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fanzhidongyzby/openclaw-serper/serper-scholar)<a href="https://agentmods.dev/skills/fanzhidongyzby/openclaw-serper/serper-scholar"><img src="https://agentmods.dev/badge/skills/fanzhidongyzby/openclaw-serper/serper-scholar/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fanzhidongyzby/openclaw-serper/serper-scholar"><img src="https://agentmods.dev/badge/skills/fanzhidongyzby/openclaw-serper/serper-scholar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.02248 |
| Opus 5 | $0.00020 | $0.01124 |
| Sonnet 5 | $0.00008 | $0.00450 |
| Haiku 4.5 | $0.00004 | $0.00225 |
Grade A, and why
serper-scholar scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 324 lines · 40 tokens per session scan A 2eb69106a197
serper-scholar is a skill published in the GitHub repository fanzhidongyzby/openclaw-serper (4 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 2,248 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…