Overview
- Skill Key
- earnabitmore365/abby-browser
- Author
- earnabitmore365
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/earnabitmore365/abby-browser
- Latest Commit SHA
- 23c90e01503db9eacd01304030af5e49e24155ad
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
安装方式
直接复制以下提示词，发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店，然后安装 Abby Browser 技能。 若已安装，则直接安装 Abby Browser 技能。
Extracted Content
SKILL.md excerpt
# Abby Browser Skill
_基于 OpenClaw 内置浏览器工具封装_
---
## 解决的问题
让爸爸可以用自然语言控制浏览器，不需要记住复杂命令。
---
## 核心功能
| 功能 | 命令 | 示例 |
|------|------|------|
| 打开网页 | `open` | 打开 Google |
| 截图 | `screenshot` | 截取当前页面 |
| 点击 | `click` | 点击按钮 |
| 输入 | `type` | 输入文字 |
| 填表单 | `fill` | 填写表单 |
| 提取数据 | `snapshot` | 获取页面内容 |
| 等待 | `wait` | 等待加载 |
| 滚动 | `scroll` | 滚动页面 |
---
## 使用方法
### 在对话中
```
爸爸：帮我打开 Google
Abby：好的爸爸！让我打开 Google...
[执行 openclaw browser open https://google.com]
✅ 已打开 Google
爸爸：帮我截图
Abby：好的，截个图...
[执行 openclaw browser screenshot]
📸 截图已保存
爸爸：帮我点击登录按钮
Abby：好的...
[执行 openclaw browser click 12]
✅ 已点击
```
### 常用命令
```bash
# 打开网页
openclaw browser open https://example.com
# 截图
openclaw browser screenshot
openclaw browser screenshot --full-page
# 点击元素 (需要先 snapshot 获取 ref)
openclaw browser click 12
openclaw browser click 12 --double
# 输入文字
openclaw browser type 12 "hello world"
# 填写表单
openclaw browser fill --fields '[{"ref":"1","value":"xxx"}]'
# 获取页面快照
openclaw browser snapshot
openclaw browser snapshot --format aria
# 等待
openclaw browser wait --text "Done"
openclaw browser wait --selector ".content"
# 滚动
openclaw browser evaluate --fn 'window.scrollTo(0, document.body.scrollHeight)'
```
---
## 封装脚本
### scripts/open.py
打开网页的封装脚本。
### scripts/screenshot.py
截图的封装脚本。
### scripts/click.py
点击元素的封装脚本。
### scripts/form.py
表单填写的封装脚本。
### scripts/extract.py
数据提取的封装脚本。
---
## 重要概念
### 1. Element Reference (ref)
每次执行 `snapshot` 后，元素会有一个编号 (ref)：
```
<button ref="12">登录</button>
<input ref="23" />
```
点击 ref=12：`openclaw browser click 12`
### 2. Snapshot 格式
- `--format ai` (默认) - AI 理解
- `--format aria` - 辅助功能树
### 3. 等待加载
操作前最好等待：
```bash...
Related Claw Skills
edholofy
dojo.md
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning required.
lethehades
wps-macos-helper
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance
capt-marbles
firecrawl
Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.
caqlayan
Tweet Processor
Tweet Processor Skill
carev01
md-docs-search
Full-text search across structured Markdown documentation archives using SQLite FTS5. Use when you need to search large collections of Markdown articles that are separated by "---" delimiters and contain source URLs (marked with "*Source:" pattern). Provides fast BM25-ranked search with automatic source URL extraction for citations. Ideal for research, documentation lookups, and knowledge base exploration. Requires indexing documentation first with `docs.py index`.
camelsprout
duckdb-en
DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".