What makes Deep Research notable?

1K downloads. Trust evidence available

How should Deep Research be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Deep Research

Deep web research across 11 Chinese and international sources (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub). Use when t... Skill: Deep Research Owner: nb-clh Summary: Deep web research across 11 Chinese and international sources (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub). Use when t... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-20T10:43:33.734Z | user Initial release: 11-source deep search (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub) via Agentic RAG

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed May 20, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17djfax68npredjxf2nkmg6ad872chj:agentic-rag-cn

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-nb-clh-agentic-rag-cn/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

5,357 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: deep-research
description: Deep web research across 11 Chinese and international sources (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub). Use when the user asks for deep research, comprehensive search, multi-source search, or needs results from Chinese platforms (Zhihu, Bilibili, WeChat). Falls back to built-in web_search if the API is unavailable.
---

# 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:

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

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

## Usage

Call the API with a POST request:

```bash
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

_meta.json

{
  "ownerId": "kn78fndehxd4b6hhzcwyxbfcn18724qb",
  "slug": "agentic-rag-cn",
  "version": "1.0.0",
  "publishedAt": 1779273813734
}

references/api.md

# API Reference

## Endpoints

### GET /health

Health check. Returns `{"status": "ok"}` if running.

### POST /api/analyze

Main research endpoint.

**Request body:**
```json
{
  "question": "搜索问题"
}
```

**Response:**
```json
{
  "answer": "结构化答案",
  "sources": [
    {"title": "...", "url": "...", "source": "baidu"}
  ],
  "confidence": 0.85,
  "contradictions": [],
  "trace": {
    "elapsed_seconds": 12.5,
    "steps": ["web_search", "vector_search", "..."]
  }
}
```

### POST /search

Raw search without RAG pipeline. Returns unprocessed search results.

**Request body:** Same as `/api/analyze`.

## Error Codes

| Code | Meaning |
|------|---------|
| 200 | Success |
| 422 | Invalid request body |
| 500 | Internal error |
| 503 | Service unavailable |

skill-card.md

## Description:

Deep web research across 11 Chinese and international sources (Baidu, Bing, Sogou, Quark, ChinaSo, WeChat, Yandex, Zhihu, Bilibili, V2EX, GitHub).

This skill is ready for commercial/non-commercial use.

## Publisher:

[nb-clh](https://clawhub.ai/user/nb-clh)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and research-capable agents use this skill to run multi-source deep web research, especially for Chinese platforms, through a local Agentic RAG-CN API and present answers with evidence, sources, confidence, and contradictions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Search questions are sent to a local Agentic RAG-CN service that may store logs or contact external search providers.

Mitigation: Avoid sending sensitive prompts unless you understand and accept that local service's logging and provider behavior.

Risk: The skill depends on a trusted local service running on port 18888.

Mitigation: Run the health check before use and install only when you intentionally operate or trust that local service.

## Reference(s):

- [API Reference](references/api.md)
- [ClawHub Skill Page](https://clawhub.ai/nb-clh/skills/agentic-rag-cn)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Guidance]

**Output Format:** [Markdown with answer summaries, evidence tables, contradiction notes, and source lists]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include confidence scores and source URLs returned by the local API.]

## Skill Version(s):

1.0.0 (source: ClawHub release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.