What makes deep-research notable?

1.5K 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

使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Skill: deep-research Owner: juan-xin-cai Summary: 使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-09T08:39:30.819Z | user - Clarifies dependency handling: now requires explicit use of the @google/genai NPM package and/or GOOGLE_GENAI_SDK_PATH; stops scanning multiple local c

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.5k

Updated

Oct 10, 2026

Version

1.0.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.

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 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.5K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.2release · observed Mar 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s176vmsw277cbmxftj2h1emcr183hbx1:google-deep-research

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-juan-xin-cai-google-deep-research/snapshot"

Documentation

CLAWHUB

9,826 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: deep-research
description: "使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。"
metadata:
  openclaw:
    primaryEnv: GEMINI_API_KEY
    homepage: https://www.npmjs.com/package/@google/genai
---

# Deep Research Agent

使用 Gemini Deep Research Pro 执行自主多步搜索-阅读-分析的深度研究，通常需要 5-20 分钟完成。

## 依赖来源

- 首选 SDK 来源：npm 包 `@google/genai`
- 可选兼容模式：通过 `GOOGLE_GENAI_SDK_PATH` 显式指定一个本地 SDK 路径

不要依赖某台开发机上的隐式 bundled SDK 路径，也不要在技能里写死个人机器目录。

## 工作流程

### 1. 确认研究主题

- 与用户确认研究主题和范围
- 如果话题模糊，帮助用户明确研究方向和关注点
- 将用户需求转化为清晰的英文或中文研究查询

### 2. 准备 API Key

必须显式提供：

```bash
export GEMINI_API_KEY="<api_key>"
```

不要自动读取本地 `openclaw.json` 或扫描多个默认配置位置。发布型技能应让密钥来源保持明确、可审查、可控。

### 3. 执行研究

**提醒用户**：深度研究通常需要 5-20 分钟，请耐心等待。

脚本与 `SKILL.md` 位于同一目录。执行时先把脚本路径解析为当前技能目录下的 `deep-research.mjs`，不要写死开发机绝对路径。

运行脚本：

```bash
GEMINI_API_KEY="<api_key>" node <skill-dir>/deep-research.mjs "<研究主题>"
```

可选参数：

- `--timeout <seconds>` — 超时时间，默认 3600 秒（1 小时）
- `--no-stream` — 使用轮询模式（如果流式出错可尝试）

可选 SDK 路径覆盖：

```bash
GOOGLE_GENAI_SDK_PATH="/path/to/@google/genai/dist/node/index.mjs" \
GEMINI_API_KEY="<api_key>" \
node <skill-dir>/deep-research.mjs "<研究主题>"
```

**重要**：由于研究耗时较长，使用 exec 工具时设置足够的超时时间（至少 1200 秒）。

### 4. 后续追问

研究完成后，脚本会输出 Interaction ID。如果用户需要追问或深入某个方面：

```bash
GEMINI_API_KEY="<api_key>" node <skill-dir>/deep-research.mjs --follow-up <interaction_id> "<追加问题>"
```

### 5. 呈现结果

- stdout 输出为 Markdown 格式的研究报告
- 保持原始 Markdown 格式呈现给用户
- 报告包含引用来源链接
- 如果用户需要，可以将报告保存为文件

## 输出说明

- **stdout** — 最终研究报告（Markdown 格式）
- **stderr** — 进度信息：
  - 🔬 研究开始
  - 📊 状态更新
  - 💭 思考摘要（Agent 的中间思考过程）
  - ✅ 研究完成 + 耗时
  - 📎 Interaction ID（用于后续追问）

## 错误处理

| 退出码 | 含义 | 处理方式 |
|--------|------|----------|
| 0 | 成功 | 正常呈现报告 |
| 1 | 参数错误 | 检查研究主题是否提供 |
| 2 | 环境或 API 错误 | 检查 `GEMINI_API_KEY`、`@google/genai` 安装和配额 |
| 3 | 超时 | 建议缩小研究范围或增加超时 |

## 安全

- 不要将 API Key 直接展示给用户
- 使用环境变量传递 API Key，不要把真实密钥写进技能文件
- 不要在未获用户确认前读取本地配置中的潜在密钥

_meta.json

{
  "ownerId": "kn7c2bjkpmjpv66zts0py6tt65814y9c",
  "slug": "google-deep-research",
  "version": "1.0.2",
  "publishedAt": 1773045570819
}

skill-card.md

## Description:

Uses Gemini Deep Research Agent to run autonomous multi-step research and produce detailed Markdown reports with citations.

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

## Publisher:

[juan-xin-cai](https://clawhub.ai/user/juan-xin-cai)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent users use this skill to turn a research topic into a long-running Gemini Deep Research session, then present the resulting cited Markdown report and support follow-up questions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill requires a Gemini API key and sends research prompts to Gemini.

Mitigation: Use an approved Gemini API key and avoid submitting secrets or sensitive data unless that use is authorized.

Risk: The optional GOOGLE_GENAI_SDK_PATH override can execute local JavaScript with the same environment as the skill, including access to the Gemini API key.

Mitigation: Prefer the default @google/genai package, or set GOOGLE_GENAI_SDK_PATH only to a fully trusted SDK file.

## Reference(s):

- [@google/genai NPM package](https://www.npmjs.com/package/@google/genai)
- [ClawHub skill page](https://clawhub.ai/juan-xin-cai/skills/google-deep-research)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown report on stdout, with progress status and follow-up interaction ID on stderr]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Reports may include citation links; runs can be streamed or polled and may take 5-20 minutes.]

## Skill Version(s):

1.0.2 (source: 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 17h 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.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular