ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified utilities Safety 4/5

web-monitor

Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, monitor for new posts/content, set up page change alerts, or check if a site has been updated. Supports CSS selectors for targeted monitoring.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bloodandeath/keats-web-monitor
Or

What This Skill Does

The web-monitor skill provides a robust way for the OpenClaw agent to track web content updates. Instead of manually refreshing pages to catch price drops or new blog posts, this tool automates the process by taking recurring snapshots of HTML content. It includes advanced functionality like CSS selector targeting, allowing you to ignore page-wide noise (like sidebars or footer links) and focus exclusively on high-value data such as specific product pricing tables, news feeds, or status updates. The agent computes diffs between snapshots, providing you with a clear view of exactly what has changed over time.

Installation

You can install this skill directly via the clawhub registry. Run the following command in your terminal: clawhub install openclaw/skills/skills/bloodandeath/keats-web-monitor Ensure you have beautifulsoup4 installed, as it is required for handling CSS selectors. You can customize the storage directory by setting the WEB_MONITOR_DIR environment variable, which is highly recommended when integrating with agent workspaces to ensure persistence across sessions.

Use Cases

This skill is perfect for users who need to stay updated on static or semi-dynamic content. Common use cases include:

  • E-commerce tracking: Monitor a specific product page for price fluctuations or stock availability changes.
  • Content curation: Track a personal blog or news site for new post announcements.
  • Service status: Keep an eye on status pages or documentation updates that lack automated RSS feeds.
  • Market research: Watch competitor websites for updates to feature lists or pricing tiers.

Example Prompts

  • "Start monitoring the pricing page at https://example.com/pricing and let me know if the price of the Enterprise tier changes."
  • "What is the current status of the content I'm tracking for my daily report? Please show me a diff of the latest update."
  • "Can you add the news section of the company website to my watch list, but only focus on the #main-news-feed container?"

Tips & Limitations

To minimize false positives, take advantage of the --selector flag to target specific DOM elements rather than the whole page. Keep in mind that this skill performs raw HTML fetching; it is not suited for JavaScript-heavy Single Page Applications (SPAs) that render content after the initial page load. For complex dynamic sites, you may need to monitor specific API endpoints instead. Always check the watches.json file in your data directory if you need to manually audit your current configuration.

Metadata

Stars4190
Views1
Updated2026-04-18
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bloodandeath-keats-web-monitor": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#web-scraping#automation#monitoring#productivity
Safety Score: 4/5

Flags: network-access, file-write, file-read

Related Skills

design-engineering

Orchestrate iterative design and frontend engineering work through research, planning, sub-agent execution, and validation loops. Use when a visual/UI task requires multiple iterations, when the first implementation needs refinement based on feedback, when choosing between competing technical approaches (Canvas vs SVG vs CSS), or when coordinating sub-agents on design-heavy work. Covers animation architecture decisions, progressive enhancement patterns, performance-aware rendering choices, and the research→plan→execute→validate workflow. Complements frontend-design (which handles aesthetics) by adding engineering discipline, iteration management, and technical decision-making.

bloodandeath 4190

agent-cost-monitor

Real-time token usage and cost tracking across all your OpenClaw agents — alerts, budgets, and optimization tips

bloodandeath 4190

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

bloodandeath 4190

code-reviewer

Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.

bloodandeath 4190

code-reviewer

Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.

bloodandeath 4190