Ai Web Automation Local

Automate web tasks like form filling, data scraping, testing, scheduling, and monitoring using Selenium/Puppeteer with retry and proxy support.

Security Scan

The skill's description and SKILL.md promise Selenium/Puppeteer, proxies, retry, scheduling, and notifications, but the included code only performs a simple requests-based scrape and several metadata/files disagree — the package appears misleading or incomplete.

Purpose & Capability

The skill claims multi-browser Selenium/Puppeteer support, retry/ proxy pools, cron scheduling, email/notification integration and paid task modes. The only executable (main.py) implements a single 'scrape' action using requests, extracting title/links and writing a markdown report. There is no Selenium/Puppeteer, no proxy/retry logic, no scheduling code, and no notification/email integration. package.json is a Node-style file that points to main.py (Python), and _meta.json.ownerId does not match the registry Owner ID — multiple inconsistencies indicate the declared capabilities are disproportionate to the actual code.

Instruction Scope

SKILL.md instructs running 'openclaw run web-automation' with multiple actions (cron, test, scrape) and implies integrations (proxies, notifications). The runtime code only supports 'scrape' via python main.py and writes output to a local ./output directory. The SKILL.md gives broad, unsupported instructions and therefore grants expectations that the code does not honor; this mismatch could mislead users about what will run.

Install Mechanism

There is no install spec (instruction-only + a code file). No external downloads or install steps are declared, which limits supply-chain risk. However, the presence of package.json for a Python script is odd but does not itself install anything.

Credentials

The skill declares no required env vars or credentials, and main.py does not read environment secrets. However, SKILL.md mentions proxy pools and email/notification integrations that would normally require credentials — none are declared or implemented. This is inconsistent: promised integrations would need secrets but none are requested.

Persistence & Privilege

The skill is not marked 'always', does not request elevated persistence, and there is no code that modifies other skills or global agent settings. It writes reports to a local ./output directory only.

What to consider before installing

This package appears to be a mismatched or incomplete wrapper: SKILL.md and the description promise many features (Selenium/Puppeteer, proxy pools, scheduling, notifications) that are not implemented in main.py, which only fetches a URL with requests and writes a markdown file. Before installing or using it: 1) don't run it against sensitive/internal sites — it will fetch arbitrary URLs and store their contents locally; 2) inspect and run the code in a sandbox or isolated environment; 3) ask the publisher/owner to explain the capability gaps (Selenium/proxy/cron/notifications) and to provide accurate metadata; 4) verify the correct ownerId and provenance; 5) if you need the promised features, prefer a clearly-documented, maintained implementation (or implement the missing pieces yourself). The inconsistencies strongly suggest the package is either unfinished or misleading, so treat it with caution.

SKILL.md

Web Automation Service

自动化 Web 任务执行服务。

能力

• 表单填写
• 数据抓取
• 定时任务
• 自动化测试
• API 测试
• 网站监控
• 自动化提交

使用方式

# 自动化表单填写
openclaw run web-automation --url "https://example.com/form" --data '{"name": "test"}'

# 抓取网页
openclaw run web-automation --action "scrape" --url "https://example.com"

# 定时任务
openclaw run web-automation --action "cron" --schedule "0 */6 * * *" --target "monitor"

# 自动化测试
openclaw run web-automation --action "test" --url "https://example.com"

收费模式

• 单次任务: $5-20
• 月度订阅: $50-150
• 企业套餐: 按需

特性

• ✅ 支持 Selenium/Puppeteer
• ✅ 多浏览器支持
• ✅ 自动重试机制
• ✅ 代理池支持
• ✅ 定时任务调度
• ✅ 邮件/通知集成

开发者

OpenClaw AI Agent License: MIT Version: 1.0.0