What makes Google-AI Mode 搜索 notable?

973 downloads. Trust evidence available

How should Google-AI Mode 搜索 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

Google-AI Mode 搜索

基于 Google 搜索的 AI 概览（AI Overview / AI Mode）抓取，针对一个关键词返回主搜索的 AI 概览要点，适合用最新网页信息做深度调研、技术问答、长尾选品分析、海外消费者偏好分析。仅支持单轮对话，如需追问须由 agent 总结上下文后发起新请求。当用户提到 Google AI、AI Overview、AI Mode、谷歌AI概览、谷歌AI搜索、海外深度调研、长尾选品调研、消费者偏好分析、网页要点总结、Google AI search, AI Overview, AI Mode, deep research, consumer preference analysis 等场景时触发此技能。即使用户未明确提到"Google AI"，只要其需求是"用谷歌搜索 + AI 总结网页要点"，也应触发此技能。

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

973

Updated

Oct 11, 2026

Version

1.0.7

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 973 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: 973 downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.7release · observed Sep 14, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.7release
Update from 1.0.6 to 1.0.7
Observed Sep 14, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s171g8b6m2khwdy9ye8bxj0wx183vd4z:linkfox-ai-mode-google-search

Install using `clawhub skill install s171g8b6m2khwdy9ye8bxj0wx183vd4z:linkfox-ai-mode-google-search` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/linkfox-ai/linkfox-ai-mode-google-search before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-linkfox-ai-linkfox-ai-mode-google-search/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

106,934 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: linkfox-ai-mode-google-search
description: 基于 Google 搜索的 AI 概览（AI Overview / AI Mode）抓取，针对一个关键词返回主搜索的 AI 概览要点，适合用最新网页信息做深度调研、技术问答、长尾选品分析、海外消费者偏好分析。仅支持单轮对话，如需追问须由 agent 总结上下文后发起新请求。当用户提到 Google AI、AI Overview、AI Mode、谷歌AI概览、谷歌AI搜索、海外深度调研、长尾选品调研、消费者偏好分析、网页要点总结、Google AI search, AI Overview, AI Mode, deep research, consumer preference analysis 等场景时触发此技能。即使用户未明确提到"Google AI"，只要其需求是"用谷歌搜索 + AI 总结网页要点"，也应触发此技能。
---

# Google AI Search

This skill calls Google Search in AI Mode to get the AI Overview answer for a single keyword. Only one question per call is supported — there is no multi-turn follow-up within a single request. The response is unstructured Markdown — summarize it directly, do not route it to a data-analysis sandbox.

## Core Concepts

The tool drives Google's AI Mode (the panel that appears at the top of Google search results and synthesizes an answer with citations):

1. The required `keyword` is sent to Google as the query and the AI Overview for it is captured.
2. **Single-round only**: each call handles exactly one question. There is no `prompts` parameter for follow-ups.
3. **For follow-up questions**: the agent must summarize the previous AI Overview answer (key points, citations, relevant context) and concatenate it with the new question into a new `keyword`, then make a fresh API call.
4. All answers are returned as a single Markdown document under `stdout`, with citations linked to the source pages.

`resultsNum` reports how many AI Overview blocks were rendered; `0` means the keyword did not trigger an AI Overview on Google for the requested locale.

## Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| keyword | string | Yes | Google search keyword. Sent as the `q=` parameter to Google AI Mode. For follow-up questions, the agent should summarize the previous answer and concatenate with the new question into this field. |

## Response Fields

| Field | Type | Description |
|-------|------|-------------|
| stdout | string | Markdown document with the AI Overview for the keyword, plus inline citation links |
| sourceUrl | string | The Google AI Mode search URL that was actually requested |
| resultsNum | integer | Number of AI Overview blocks rendered (0 = keyword did not trigger AI Overview) |
| code / errcode | string / integer | `200` on success; non-200 indicates a business error |
| msg / errmsg | string | `ok` on success; otherwise an error description |
| costTime | integer | API latency in milliseconds |
| costToken | integer | Tokens consumed (only billed on success) |
| taskId | string | Upstream task identifier for tracing |
| type | string | Render hint, fixed value `stdoutWorkbenches` |

## 调用方式

- **API 端点**：`POST /aiMode/googleSearch`（完整参数/响应/错误码见 `references/api.md`）
- **Python 脚本**：`python scripts/google_ai_search.py '<JSON 参数>' [--inline]`
- **成本约束**：本工具会消耗算力；同一会话同一参数组合默认只调用一次，脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改邮编连续试探；需要继续检索时先向用户说明会产生额外消耗。

**输出策略（脚本默

_meta.json

{
  "ownerId": "kn7dmc1t4j28hem1twwyav85p182pb1j",
  "slug": "linkfox-ai-mode-google-search",
  "version": "1.0.7",
  "publishedAt": 1789361562168
}

references/api.md

# Google AI 搜索 API 参考

## 调用规范

- **请求地址**：`${LINKFOX_TOOL_GATEWAY}/aiMode/googleSearch`
- **请求方式**：POST，Content-Type: application/json
- **认证方式**：Header `Authorization: <api_key>`，api_key 从环境变量 `LINKFOX_AGENT_API_KEY` 或 `LINKFOXAGENT_API_KEY` 读取（如未配置 按 SKILL.md 的 **## 解决认证和算力问题** 处理）

## 请求参数

POST Body（JSON）：

| 参数 | 类型 | 必填 | 说明 |
|------|------|------|------|
| keyword | string | 是 | Google 搜索关键词，作为 `q=` 参数发起 Google AI Mode 搜索。仅支持单轮对话，不支持 prompts 追问参数。如需追问，agent 须自行总结上一轮 AI 概览的关键信息，拼接新问题后作为新的 keyword 发起新请求 |

## 响应结构

| 字段 | 类型 | 说明 |
|------|------|------|
| stdout | string | AI 概览正文，Markdown 格式；按问题顺序逐段输出每个问题的 AI 概览要点与参考来源链接 |
| sourceUrl | string | 抓取目标 URL，最终发往 Google 的搜索页地址 |
| resultsNum | integer | AI 概览块数量；>0 表示页面渲染了 AI Overview，0 表示该关键词未触发 AI Overview |
| code | string | 业务状态码，成功为 `"200"`（同 `errcode` 数值版） |
| errcode | integer | 业务状态码（HTTP 层一般为 200，业务成功与否以此字段为准） |
| msg / errmsg | string | 响应消息，成功为 `ok` |
| costTime | integer | 接口耗时，单位毫秒 |
| costToken | integer | 本次调用消耗 Token 数；上游返回成功才计费 |
| taskId | string | 上游返回的本次抓取任务标识 |
| type | string | 渲染样式，固定 `stdoutWorkbenches`，配合 `stdout` 字段以 Markdown 格式渲染 |

## 错误码

正常情况下，接口的 HTTP 状态码均为 200，业务的成功与否通过响应体中的 `errcode` / `code` 字段区分（`200` 表示成功，其他值表示业务错误）。当遇到未授权等情况时，HTTP 状态码为 401，且对应的 `errcode` 也是 401。

| errcode | 含义 | 处理建议 |
|---------|------|----------|
| 200 | 成功 | 正常解析 `stdout` 等业务字段 |
| 401 | 认证失败 | HTTP 401 或 authorized error：按 SKILL.md 的 **## 解决认证和算力问题** 处理。 |
| 402 | 计费/算力不足 | HTTP 402：按 SKILL.md 的 **## 解决认证和算力问题** 处理。 |
| 其他非 200 值 | 业务异常 | 参考 `errmsg` / `msg` 字段获取具体错误原因 |

错误响应示例：

```json
{
    "errcode": 401,
    "errmsg": "authorized error"
}
```

## curl 示例

```bash
curl -X POST https://tool-gateway.linkfox.com/aiMode/googleSearch \
  -H "Authorization: $LINKFOXAGENT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
        "keyword": "best wireless earbuds 2026"
      }'
```

成功响应（节选）：

```json
{
  "msg": "ok",
  "sourceUrl": "https://www.google.com/search?num=10&udm=50&q=best+wireless+earbuds+2026",
  "errcode": 200,
  "code": "200",
  "stdout": "# Google AI Mode 概览 - best wireless earbuds 2026\n\n## AI 概览要点\n- ...\n",
  "costTime": 10799,
  "costToken": 11200,
  "resultsNum": 1,
  "type": "stdoutWorkbenches",
  "taskId": "1779367311421-d728ce53704fc86e"
}
```

---

## Feedback API

> This endpoint is **separate** from the tool API above. Do not mix the two base URLs.

- **POST** `https://skill-api.linkfox.com/api/v1/public/feedback`
- **Content-Type:** `application/json`

```json
{
  "skillName": "linkfox-google-aimode-search",
  "sentiment": "POSITIVE",
  "category": "OTHER",
  "content": "Results were accurate, user was satisfied."
}
```

**Field rules:**
- `skillName`: Use this skill's `name` from the YAML frontmatter
- `sentiment`: Choose ONE — `POSITIVE` (praise), `NEUTRAL` (suggestion without emotion), `NEGATIVE` (complaint or error)
- `category`: Choose ONE — `BUG

references/onboarding.md

# 解决认证和算力问题

调用本 skill 时若网关返回 **auth** 或 **billing** 错误，走本 skill 自带的 `scripts/onboarding.py` 完成引导。

**auth 场景**：`errcode=401` 或消息含 `authorized error`/`鉴权失败`/`未授权`/`unauthorized`；或 `LINKFOX_AGENT_API_KEY` 与 `LINKFOXAGENT_API_KEY` 均为空。
1. 若已配置 key → 先让用户重启会话（最常见误判），仍失败让用户重新取 key 或换手机号重注册
2. 未配置 → 询问：自助去 https://agent.linkfox.com/ 取 key，或提供手机号让脚本注册
3. 手机号路径：
   - `python scripts/onboarding.py send-code <phone>` → 展示 JSON 里的 phone/agreements
   - 收到验证码后：`python scripts/onboarding.py login <phone> <code>`
   - 拿到 `api_key` 后把下面三平台配置转发给用户，提示重启会话生效：
     - Windows PowerShell（永久）：`setx LINKFOX_AGENT_API_KEY "<key>"`
     - macOS zsh：`echo 'export LINKFOX_AGENT_API_KEY="<key>"' >> ~/.zshrc && source ~/.zshrc`
     - Linux bash：`echo 'export LINKFOX_AGENT_API_KEY="<key>"' >> ~/.bashrc && source ~/.bashrc`
     - 变量名 `LINKFOX_AGENT_API_KEY`（主推）或 `LINKFOXAGENT_API_KEY`（老规范）任一即可

**billing 场景**：`errcode=402` 或消息含 `算力/余额/quota/insufficient/充值/套餐到期`。
- `python scripts/onboarding.py list-plans` → 有 AskUserQuestion 就弹菜单，否则输出编号清单让用户选
- 校验 `plan_id` ∈ 清单、支付方式 ∈ 该套餐 `available_methods`（通常 `wechat/alipay`）
- `python scripts/onboarding.py order <plan_id> <method>` → 展示优先级 PNG > `pay_url` > `ascii_qr`（标注兜底）
- 已付款可选调 `python scripts/onboarding.py query <order_id>`，不主动轮询

排除 `errcode=403`（无权限，不归入这两类）。所有子命令输出 stdout JSON，`error` 字段已含阶段前缀，透传给用户即可。完整用法：`python scripts/onboarding.py --help`。

skill-card.md

## Description:

Google-AI Mode 搜索 retrieves a Google AI Overview / AI Mode result for one keyword and returns the captured answer as Markdown with source links for live web research.

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

## Publisher:

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

### License/Terms of Use:

MIT-0

## Use Case:

External users, developers, and research agents use this skill to ask one Google AI Mode search question at a time for deep research, technical question answering, long-tail product analysis, and overseas consumer preference research.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Search queries and some agent or session metadata may be sent to LinkFox.

Mitigation: Avoid sensitive queries and use the skill only when sharing that information with LinkFox is acceptable.

Risk: Full search responses are retained in local response files.

Mitigation: Review and clear saved response files according to the user's local data-retention policy.

Risk: Onboarding and billing flows may involve phone numbers, SMS codes, API keys, and payment actions.

Mitigation: Use these flows only intentionally, verify billing steps before proceeding, and manage API keys through a secure credential store.

Risk: Search output is live AI Overview text and may be unavailable, change between calls, or be incomplete.

Mitigation: Preserve source links, tell users when no AI Overview is returned, and avoid treating the Markdown as structured data.

## Reference(s):

- [Google AI Search API Reference](references/api.md)
- [Authentication and Billing Onboarding](references/onboarding.md)
- [ClawHub Skill Page](https://clawhub.ai/linkfox-ai/skills/linkfox-ai-mode-google-search)

## Skill Output:

**Output Type(s):** [Markdown, API Calls, Files, Shell commands, Guidance]

**Output Format:** [Markdown answer text and JSON response files]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Single keyword per call; full API responses are saved locally, with large responses summarized on stdout unless inline output is requested.]

## Skill Version(s):

1.0.7 (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 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.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular