firecrawl-monitor

Creates recurring web monitors that detect page changes and send webhook or email alerts.

Updated Aug 2, 2026
One-click install
npx skills add https://github.com/leonardoacosta/agents --skill firecrawl-monitor-leonardoacosta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-monitor
Source: https://github.com/leonardoacosta/agents/tree/main/skills/firecrawl-monitor
Command: npx skills add https://github.com/leonardoacosta/agents --skill firecrawl-monitor-leonardoacosta

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Repeatedly checking websites by hand for new content, price changes, or competitor announcements is tedious and error-prone. This Skill sets up recurring Firecrawl monitors that fetch, diff, and judge pages server-side, then notify you by webhook or email only when something meaningful changed. ## Core Features & Use Cases - Four target modes: watch a single page, a batch of URLs, an entire crawled site, or the whole web via search queries plus a goal. - AI-judged change detection: each checked page is labeled same, new, changed, removed, or error, with natural-language goals controlling what counts as a real change. - Structured JSON tracking: per-field diffs (e.g. plans[0].price: "$19/mo" → "$24/mo") that drop directly into Slack messages, CI steps, or internal tools. - Use Case: Create a daily web monitor with queries like "competitor product launch" and a goal to alert on new product announcements, delivered to a webhook endpoint. ## Quick Start Ask the AI to create a Firecrawl monitor that checks a specific URL on a schedule and emails you when its content changes.

Frequently Asked Questions about firecrawl-monitor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor a webpage for changes with Firecrawl?

Run firecrawl monitor create with --page for the URL, --schedule for a natural-language interval like "every 30 minutes", a --goal describing what counts as a change, and --email or --webhook-url for notifications. The command returns a monitor ID you can inspect or trigger manually.

How do I track new web results for a search query automatically?

Create a web monitor with --queries for keyword searches plus a required --goal describing what should alert. Firecrawl runs the queries each check and labels unseen matching results as new, with --search-window and --max-results controlling recency and volume.

Can Firecrawl monitors track specific fields like prices instead of whole pages?

Yes, JSON-mode change tracking returns per-field diffs such as plans[0].price changes instead of markdown diffs. Pass a JSON body with a changeTracking format, extraction prompt, and schema to firecrawl monitor create via a file or piped stdin.

What are the limitations of Firecrawl monitoring?

The minimum schedule interval is 5 minutes, monitoring is unavailable for zero-data-retention teams, and each check consumes credits for its scrape, crawl, or search plus optional judging. External email recipients must also confirm an opt-in message before receiving alerts.

What should I do when Firecrawl monitor returns a 429 rate-limit error?

Back off once by waiting about 30 seconds and retrying a single time. If the error persists, stop, report the rate limit as the blocking reason, and delete any monitors created for the task rather than retrying in a loop.