← 返回 Skills 市场
nb-clh

Deep Research

作者 nb-clh · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
41
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agentic-rag-cn
功能描述
Deep web research across 11 Chinese and international sources (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub). Use when t...
使用说明 (SKILL.md)

Deep Research

Search across 11 sources simultaneously via a local Agentic RAG-CN API, then synthesize results with evidence tables and contradiction detection.

Prerequisites

Agentic RAG-CN must be running locally. Check with:

curl -s http://localhost:18888/health

If unavailable, fall back to built-in web_search tool.

Usage

Call the API with a POST request:

curl -s -X POST http://localhost:18888/api/analyze \
  -H "Content-Type: application/json" \
  -d '{"question": "用户的问题"}'

Parse the JSON response and present results to the user in a readable format.

Response Format

The API returns:

  • answer — Structured answer with evidence tables
  • sources — List of sources used (with URLs)
  • confidence — Confidence score (0-1)
  • contradictions — Any contradictions found across sources
  • trace — Pipeline execution trace (16 steps)

When to Use vs Fallback

Condition Action
API health check succeeds Use deep-research API
API health check fails Fall back to web_search
User asks about Chinese topics (知乎, B站, 微信) Prefer deep-research
User asks general English questions web_search is usually sufficient

Presenting Results

Format the response as:

  1. Answer summary — 2-3 sentences
  2. Evidence table — Key findings with sources
  3. Contradictions (if any) — Highlight conflicting info
  4. Sources — Numbered list of URLs
安全使用建议
Treat this as an incomplete review: the requested workspace inspection failed before metadata.json or artifact files could be read, so installation should wait for a successful artifact review.
能力评估
Purpose & Capability
Not assessable from artifacts because metadata.json and artifact contents could not be read in this run.
Instruction Scope
Not assessable from artifacts because the local inspection command failed before SKILL.md or related files could be reviewed.
Install Mechanism
Not assessable from artifacts because install metadata and file contents could not be inspected.
Credentials
Not assessable from artifacts because capability and runtime evidence was unavailable.
Persistence & Privilege
Not assessable from artifacts because persistence, credential, and privilege instructions could not be inspected.
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 agentic-rag-cn
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /agentic-rag-cn 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
v1.0.0
Initial release: 11-source deep search (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub) via Agentic RAG-CN
元数据
Slug agentic-rag-cn
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Deep Research 是什么?

Deep web research across 11 Chinese and international sources (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub). Use when t... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 41 次。

如何安装 Deep Research?

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

Deep Research 是免费的吗?

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

Deep Research 支持哪些平台?

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 Deep Research?

由 nb-clh(@nb-clh)开发并维护,当前版本 v1.0.0。

💬 留言讨论