← 返回 Skills 市场
Research-engine
作者
guogang1024
· GitHub ↗
· v1.0.0
4977
总下载
5
收藏
41
当前安装
1
版本数
在 OpenClaw 中安装
/install research-engine
功能描述
自动化多源信息收集与趋势分析，生成结构化研究报告并制定阶段性开发计划，助力技术探索与规划。
安全使用建议
Review before installing. Use it only for topics you are comfortable sending to external sources and storing locally, avoid sensitive topics unless retention is acceptable, and do not enable cron or autonomous integrations without explicit limits. The developer should sanitize report filenames and document retention, deletion, and dependency requirements.
功能分析
Type: OpenClaw Skill
Name: research-engine
Version: 1.0.0
The skill is an automated research engine designed to gather information from external sources like GitHub, Moltbook, and general web search. It uses OpenClaw's built-in `web_fetch` and `web_search` tools for external access, which are assumed to be controlled and sandboxed by the agent environment. All generated research reports and browsing history are saved locally within the agent's designated workspace (`/home/vken/.openclaw/workspace/research`), as specified in `SKILL.md` and implemented in `research_engine.py`. There is no evidence of credential theft, data exfiltration to unauthorized external endpoints, malicious execution, persistence mechanisms, or prompt injection attempts to subvert the agent's core directives. The `subprocess` module is imported in `research_engine.py` but is not used.
能力评估
Purpose & Capability
Web, GitHub, Moltbook collection and Markdown report generation fit the stated research-engine purpose; the broader self-development framing and proactive exploration expand the expected behavior beyond simple user-requested reports.
Instruction Scope
The documentation says the agent can actively search without waiting for instructions and describes hourly, daily, and three-hour integrations, but does not define user approval, cadence limits, or stop controls for recurring network research.
Install Mechanism
The package has no install scripts or declared dependencies, but the Python code imports ambient platform modules and a Moltbook skill, so actual external access depends on capabilities outside this artifact.
Credentials
The skill uses expected web/search tools, but report filenames are derived directly from the research topic; topics containing absolute paths or separators could cause writes outside the intended research directory.
Persistence & Privilege
Reports are disclosed as saved under a research directory, and the code also appends browsing history with topics, source names, counts, and timestamps; this is purpose-aligned but may retain sensitive research interests.
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-engine - 安装完成后，直接呼叫该 Skill 的名称或使用
/research-engine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 of Research Engine Skill.
- Automates research by searching multiple sources (GitHub, Moltbook, Web), analyzing trends, and generating structured reports.
- Supports automated development plan generation (short, mid, long-term) based on findings.
- Provides command-line, Python import, and scheduled integration methods.
- Designed to break through information silos and enable continuous, active exploration and self-development.
元数据
常见问题
Research-engine 是什么？
自动化多源信息收集与趋势分析，生成结构化研究报告并制定阶段性开发计划，助力技术探索与规划。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 4977 次。
如何安装 Research-engine？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install research-engine」即可一键安装，无需额外配置。
Research-engine 是免费的吗？
是的，Research-engine 完全免费（开源免费），可自由下载、安装和使用。
Research-engine 支持哪些平台？
Research-engine 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 Research-engine？
由 guogang1024（@guogang1024）开发并维护，当前版本 v1.0.0。
推荐 Skills