Crawl websites and generate hierarchical site maps with page summaries.
npx skills add https://github.com/silva2kand/silva-ide --skill site-mapper
Please help me install this Agent Skill. Skill: site-mapper Source: https://github.com/silva2kand/silva-ide/tree/main/_cowork_os_pack/package/resources/skills/site-mapper Command: npx skills add https://github.com/silva2kand/silva-ide --skill site-mapper
This Skill helps users understand the architecture and content layout of a website by creating detailed site maps and summaries, simplifying website analysis and planning.
Use the site-mapper skill to analyze the website at https://example.com and generate a detailed page hierarchy with summaries.
High-intent search queries and answers about installing and using this skill.
Generate a website structure map by specifying a root URL to crawl. The tool parses accessible pages hierarchically and produces a complete site map with page titles and summaries for inventory creation.
Website crawling automates URL discovery by parsing target sites recursively. It finds all accessible pages to build a hierarchical output, useful for understanding site architecture and performing content analysis.
Yes, website crawling can summarize page content automatically. The process parses each discovered URL to generate concise page summaries, allowing you to assess content relevance across the entire site architecture.
Yes, you need Python to run the website crawling scripts. The site mapping process relies on Python scripts to handle URL crawling, page parsing, and hierarchical site map output generation.
The best way to document website architecture is using automated crawling to map the site structure. Provide the root URL to generate a detailed page hierarchy with titles and descriptions for client documentation.
AllBeingsFutureNavigate the browser to a specified URL with a required protocol.
xenitV1Audit and implement foundational SEO practices across websites.
codataExtract and visit internal links from HTML for website crawling.
LuminairPrimeScrape web pages and extract structured content using Firecrawl.
