Xpersona
A

Agent Browser

CLAWHUB · Unverified

浏览器智能控制。自动化操作、截图、填表、数据抓取。 Skill: Agent Browser Owner: fhbillwer Summary: 浏览器智能控制。自动化操作、截图、填表、数据抓取。 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-10T15:59:19.803Z | auto Agent Browser v1.0.0 初始发布 - 智能控制浏览器,实现自动化操作、截图、表单填写和数据抓取 - 支持定时任务、批量操作与页面监控 - 集成常用浏览器(Chrome/Brave/Edge/Chromium) - 提供多项页面操作及数据导出能力 - 明确操作日志与安全规范 Archive index: Archive v1.0.0: 3 files, 2792 bytes Files: skill-card.md (2031b), SKILL.md (2361b), _meta.json (135b) File v1

62
Rank
84
Safety
14k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 14.1K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s172pxfyak6bzwerkv85j7s0zs884cn5:ws-agent-browser
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. 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-fhbillwer-ws-agent-browser--browser-2/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

4,324 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: "00000000000000000000000000000000"
    PropagateID: "00000000000000000000000000000000"
    ReservedCode1: 304502205c02c1ea86957276d0a274b909a4e0067db9ea8c5ca21de30747310b6f3dfabb022100cc035501daaa6e642da4c69ca11f72efa6fb970a6f5e26f711ebb9e3bf1ed3a9
    ReservedCode2: 3045022055ff431f1fac57a338871581c0d1ae5acd1b4c945ca1e40c60062b60cae4b531022100dd7076f1dbf9ed9d9cff03cb5b993b4f86f4988d6f289570a12a6eba8ef20409
description: 浏览器智能控制。自动化操作、截图、填表、数据抓取。
metadata:
    category: 生产力
    emoji: "\U0001F310"
    triggers:
        - 浏览器
        - browser
        - 自动化
        - 截图
        - 填表
        - 抓取
name: agent-browser
---

# Agent Browser 技能

智能浏览器控制助手。

## 功能

### 📸 页面操作
- 打开网页
- 截图/录屏
- 点击/输入
- 滚动/导航

### 🤖 自动化
- 表单自动填写
- 批量操作
- 定时任务
- 登录认证

### 📥 数据抓取
- 提取网页内容
- 表格数据导出
- 动态内容抓取
- 定期监控

### ✅ 测试
- UI 测试
- 回归测试
- 性能监控

## 使用方式

```
帮我打开这个网页并截图
URL:https://example.com

自动化操作:帮我填写这个表单
字段:姓名、电话、地址

抓取数据:把这个页面的表格导出成CSV
URL:https://example.com/data

监控:每小时检查这个页面有无更新
URL:https://example.com/status
```

## 浏览器配置

OpenClaw 内置浏览器功能。

**环境要求:**
- 需要在有浏览器的机器上运行(如本地电脑)
- 支持 Chrome/Brave/Edge/Chromium

**使用方式:**
- 直接告诉我:"打开某网页" / "截图" / "填表"
- 使用 `browser` 工具进行操作

**可用操作:**
- `browser_open` - 打开网页
- `browser_snapshot` - 页面快照
- `browser_screenshot` - 截图
- `browser_click` - 点击元素
- `browser_type` - 输入文字
- `browser_evaluate` - 执行脚本

## 安全说明

- 🔒 敏感操作需要确认
- 📝 操作日志可追溯
- ⚠️ 遵守网站 robots.txt

---

**数据存储**: 
- 截图/录屏:`/workspace/data/browser/screenshots/`
- 抓取数据:`/workspace/data/browser/data/`
- 配置:`/workspace/data/browser/config.json`

_meta.json

{
  "ownerId": "kn7er7bv6cmpabky4cparwmtkh82ny8d",
  "slug": "ws-agent-browser",
  "version": "1.0.0",
  "publishedAt": 1773158359803
}

skill-card.md

## Description:

Browser control for automated page actions, screenshots, form filling, and data extraction.

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

## Publisher:

[fhbillwer](https://clawhub.ai/user/fhbillwer)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and operators use this skill to direct an agent through browser tasks such as opening pages, taking screenshots, filling forms, exporting table data, and monitoring pages for changes.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Broad browser control can perform sensitive actions such as logins, form submissions, purchases, account changes, script execution, scraping authenticated pages, or scheduled monitoring.

Mitigation: Require explicit confirmation before sensitive actions and review requested browser operations before execution.

Risk: Screenshots, scraped data, and configuration files may contain sensitive information.

Mitigation: Check storage locations for generated browser data and delete screenshots, exports, recordings, and configuration files when no longer needed.

Risk: Automated scraping or monitoring may conflict with site rules or user expectations.

Mitigation: Respect robots.txt, site terms, and access boundaries before running extraction or monitoring tasks.

## Reference(s):


## Skill Output:

**Output Type(s):** [Guidance, Shell commands, Configuration, Files]

**Output Format:** [Markdown with browser action requests, tool names, paths, and configuration guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May produce screenshots, recordings, scraped data exports, and browser configuration files.]

## Skill Version(s):

1.0.0 (source: ClawHub release metadata)

## 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.

Sponsored

Ads related to Agent Browser and adjacent AI workflows.