← 返回 Skills 市场
10302
总下载
30
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install gemini-deep-research
功能描述
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.
安全使用建议
Install only if you are comfortable sending research prompts and any selected Gemini file-search context to Google's Gemini service. Use an environment variable rather than passing the API key on the command line on shared machines, monitor quota or cost for long-running jobs, and choose a private output directory when reports or response metadata may contain sensitive material.
功能分析
Type: OpenClaw Skill
Name: gemini-deep-research
Version: 1.0.0
The skill is designed to interact with the Gemini Deep Research API for complex research tasks. It correctly handles the `GEMINI_API_KEY` by reading it from environment variables or CLI arguments and uses it to authenticate with the legitimate Google API endpoint (`generativelanguage.googleapis.com`). The script saves research reports locally to user-specified or default directories, which is a core function. There is no evidence of unauthorized data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the OpenClaw agent, or obfuscation. All observed behaviors are aligned with the stated purpose.
能力评估
Purpose & Capability
The SKILL.md and script consistently implement a Gemini Deep Research client that submits a query, optionally references a Gemini file-search store, polls the Gemini API, extracts a report, and prints/saves results.
Instruction Scope
Usage is explicit and command-driven, and the documentation names the external Gemini endpoint and saved output files; privacy warnings for sensitive prompts or file-search context could be stronger.
Install Mechanism
The artifact contains a readable SKILL.md and one Python script, with no installer hook, bootstrapper, package download, or hidden setup behavior.
Credentials
Requiring GEMINI_API_KEY and outbound requests to generativelanguage.googleapis.com is proportional to the research purpose, but users should expect API costs and third-party processing by Google.
Persistence & Privilege
There is no startup persistence, privilege escalation, credential harvesting, or destructive behavior; the script intentionally writes timestamped markdown and JSON result files to the chosen output directory.
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 gemini-deep-research - 安装完成后，直接呼叫该 Skill 的名称或使用
/gemini-deep-research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
v1.0.0
Initial release: Complex research tasks via Gemini Deep Research Agent
元数据
常见问题
Gemini Deep Research 是什么？
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 10302 次。
如何安装 Gemini Deep Research？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install gemini-deep-research」即可一键安装，无需额外配置。
Gemini Deep Research 是免费的吗？
是的，Gemini Deep Research 完全免费（开源免费），可自由下载、安装和使用。
Gemini Deep Research 支持哪些平台？
Gemini Deep Research 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 Gemini Deep Research？
由 arun-8687（@arun-8687）开发并维护，当前版本 v1.0.0。
推荐 Skills