← 返回 Skills 市场
flying-baozi

Scholarsearch

作者 flying-baozi · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
276
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install scholarsearch
功能描述
Academic literature search and briefing generation with Tavily API, PubMed, and Google Scholar. Use when you need to search for latest academic papers on spe...
安全使用建议
This skill claims to search academic sources and automatically save/send briefings, but it omits critical implementation details. Before installing or enabling it, ask the publisher these questions: (1) What exact credentials or tokens are required (Tavily API key, Feishu app token, Obsidian vault path)? Where will you store them? (2) Where does the 'scholarsearch' binary come from and who maintains it? Is there an install step or platform-provided connector? (3) What network endpoints will be contacted (Tavily domain, Feishu API domain, any other third-party hosts)? Can you review them? (4) What data is sent to Feishu and who receives it — avoid sending protected or sensitive patient data. (5) Will the skill run on a schedule and how can you disable it? If the publisher cannot provide clear, verifiable answers or a trustworthy source/repository for the code, treat the skill as risky and prefer a vetted alternative or run it in a sandboxed environment with isolated credentials.
功能分析
Type: OpenClaw Skill Name: scholarsearch Version: 1.1.0 The 'scholarsearch' skill is a set of instructions for an AI agent to automate academic literature reviews using the Tavily API, PubMed, and Google Scholar. It defines a clear workflow for searching, ranking papers based on clinical relevance, and delivering reports to Obsidian and Feishu. The bundle contains no executable code, suspicious network calls, or malicious prompt-injection attempts, and its behavior is entirely consistent with its stated purpose as a research assistant tool.
能力评估
Purpose & Capability
The skill says it queries Tavily API and delivers results to Feishu and an Obsidian vault, yet the registry metadata declares no required environment variables, no primary credential, and no required config paths. A legitimate integration with Tavily/Feishu/Obsidian would normally require API keys, tokens, or at least a configurable vault path. The SKILL.md also demonstrates a CLI invocation (scholarsearch) but no binary or install is provided.
Instruction Scope
SKILL.md instructs searches across multiple external services and automatic saving/delivery (Obsidian path, Feishu), and suggests cron scheduling. It does not explain how to authenticate to Tavily or Feishu, nor does it limit what data may be collected or sent. The instructions implicitly assume capabilities (network access, credentials, existing 'scholarsearch' command) that are not declared, giving the agent broad discretion without documented boundaries.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only. From a supply-chain perspective this is lower risk (nothing is automatically downloaded or written by the skill), but it increases ambiguity about where the required components come from (platform, user environment, or a missing binary).
Credentials
The skill integrates with third-party services (Tavily, Feishu, Obsidian) that normally require API credentials or configuration, yet the manifest requests no env vars or config paths. This under-declaration is disproportionate to the stated functionality and could hide implicit requests for credentials at runtime or require the agent to access other system stores for authentication.
Persistence & Privilege
The skill is not always-on and uses default autonomous invocation settings. It does not declare modifications to other skills or system-wide settings. The scheduling suggestion (cron) is a user instruction rather than an enforced persistent capability in the manifest.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install scholarsearch
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /scholarsearch 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.1.0
Added fixed scoring criteria and explanation
v1.0.0
Initial release: Academic literature search with Tavily API, PubMed, Google Scholar
元数据
Slug scholarsearch
版本 1.1.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 2
常见问题

Scholarsearch 是什么?

Academic literature search and briefing generation with Tavily API, PubMed, and Google Scholar. Use when you need to search for latest academic papers on spe... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 276 次。

如何安装 Scholarsearch?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install scholarsearch」即可一键安装,无需额外配置。

Scholarsearch 是免费的吗?

是的,Scholarsearch 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Scholarsearch 支持哪些平台?

Scholarsearch 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Scholarsearch?

由 flying-baozi(@flying-baozi)开发并维护,当前版本 v1.1.0。

💬 留言讨论