← 返回 Skills 市场

Research Analyzer

Name: Research Analyzer
Author: hyqdq888

作者 hyqdq888 · GitHub ↗ · v1.0.2 · MIT-0

cross-platform ⚠ suspicious

523

总下载

当前安装

版本数

在 OpenClaw 中安装

/install research-analyzer

功能描述

综合研究分析工具 - 基于 Tavily API 的智能搜索和报告生成，支持深度研究、竞品分析、技术调研

使用说明 (SKILL.md)

Research Analyzer 🔬

基于 Tavily API 的一站式研究分析工具，智能搜索网络信息并生成结构化研究报告。

功能特性

🔍 智能搜索 - Tavily 网络搜索，LLM 优化结果
📊 数据分析 - 自动提取关键信息和趋势
📝 报告生成 - 结构化研究报告输出
🌐 双语支持 - 中英文混合搜索和分析

快速开始

基础研究

node {baseDir}/scripts/research.mjs "研究主题"

深度研究

node {baseDir}/scripts/research.mjs "研究主题" --deep --output report.md

使用场景

场景1：市场研究

node scripts/research.mjs "AI Agent 市场趋势 2025" --deep

场景2：深度研究

node scripts/research.mjs "机器学习在医疗诊断中的应用" --deep --output medical_ai_report.md

场景3：竞品分析

node scripts/research.mjs "OpenAI vs Claude vs Gemini 对比分析"

场景4：技术调研

node scripts/research.mjs "Rust vs Go 性能对比"

参数说明

参数	说明	默认值
`--deep`	深度搜索模式	false

输出格式

标准报告

# 研究报告: [主题]

## 执行摘要
...

## 关键发现
...

## 数据来源
...

## 结论与建议
...

依赖配置

需要设置 Tavily API Key（仅通过环境变量）：

export TAVILY_API_KEY="tvly-xxx"

安全说明:

API Key 仅通过环境变量读取
不会读取任何本地配置文件
不会访问用户敏感目录

许可

MIT License

安全使用建议

This skill appears internally consistent, but review these practical points before installing: (1) The tool sends your query text to Tavily's API — do not include secrets or confidential data in queries. (2) You must supply a valid TAVILY_API_KEY; ensure the key has appropriate (least) privileges and is trusted. (3) The script may write a report file if you use --output; run it in a directory where that is safe. (4) Verify you trust the Tavily endpoint (https://api.tavily.com) and the skill source (GitHub repo link) before providing credentials. (5) Ensure your Node runtime supports global fetch (Node 18+ or equivalent) to avoid runtime errors.

功能分析

Type: OpenClaw Skill Name: research-analyzer Version: 1.0.2 The research-analyzer skill is a legitimate tool designed to perform web searches and generate reports using the Tavily API. The core logic in scripts/research.mjs is transparent, correctly handles API keys via environment variables, and lacks any indicators of malicious intent such as data exfiltration, unauthorized file access, or obfuscation.

能力评估

✓ Purpose & Capability

Name/description match the implementation: the script performs a POST to https://api.tavily.com/search, uses TAVILY_API_KEY for Authorization, and produces reports. Requiring Node and a Tavily API key is appropriate for this functionality.

✓ Instruction Scope

SKILL.md instructs running the included Node script with a query and optional flags. The script only reads the TAVILY_API_KEY environment variable and writes an optional output file; it does not access other local config paths or broad system state. No extra data collection or unexpected endpoints are present.

✓ Install Mechanism

No install spec; this is an instruction-only skill with a small script that runs under node. Nothing is downloaded or written to system directories during install, minimizing install-time risk.

✓ Credentials

Only a single environment variable (TAVILY_API_KEY) is required and is the declared primary credential. That is proportional and expected for a service-backed search/reporting tool.

✓ Persistence & Privilege

The skill does not request permanent/always-on presence. It does not modify other skills or system-wide settings. Normal agent autonomy (disable-model-invocation=false) is unchanged.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install research-analyzer
安装完成后，直接呼叫该 Skill 的名称或使用 /research-analyzer 触发
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

v1.0.2

修复：移除未使用的 curl 依赖，清理未实现的功能参数，更新文档描述

v1.0.1

Security fix: Remove .env file reading, only use environment variable for API key

v1.0.0

Initial release - 综合研究分析工具，支持多源搜索和报告生成

元数据

Slug research-analyzer

版本 1.0.2

许可证 MIT-0

累计安装 7

当前安装数 7

历史版本数 3

常见问题