ms-crawl

Crawl corporate websites across four sources to map URL inventory and classify content sections.

1|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/MB-uc/mercury --skill ms-crawl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ms-crawl
Source: https://github.com/MB-uc/mercury/tree/main/mercury/skills/ms-crawl
Command: npx skills add https://github.com/MB-uc/mercury --skill ms-crawl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill solves the challenge of incomplete or unreliable website auditing by automating a rigorous, four-source discovery process that ensures no content is missed during consultant research.

Core Features & Use Cases

  • Multi-Source Discovery: Aggregates data from sitemaps, HTML navigation, full-site crawls, and pagination loops to build a comprehensive URL inventory.
  • Evidence-Based Verification: Performs strict negative verification to confirm the absence of content, preventing false claims.
  • Structured Output: Generates a hierarchical site structure and evidence manifest for seamless integration into downstream analysis.

Quick Start

Run the ms-crawl skill to perform a full site discovery and generate the evidence manifest for the target company domain.

Frequently Asked Questions about ms-crawl

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

FAQPage Schema
How do I automate corporate website discovery for a comprehensive site audit?

Automated corporate website discovery uses a multi-source crawl process to map URL inventory and classify content sections. It aggregates data from sitemaps, HTML navigation, full-site crawls, and pagination loops to build a complete site structure for strategic audits.

What is negative verification in website crawling and why does it matter?

Negative verification in website crawling confirms the verified absence of specific content rather than simply missing it. This prevents false claims during evidence-based audits by strictly validating that content does not exist across the crawled site sources.

How do I build a complete URL inventory from a corporate domain?

Building a complete URL inventory requires aggregating data from four sources: sitemaps, HTML navigation links, full-site crawls, and pagination loops. This multi-source approach ensures no content sections are missed during the corporate site discovery process.

Does the ms-crawl skill require firecrawl to perform full site discovery?

Yes, the ms-crawl skill requires firecrawl to execute its comprehensive four-source discovery process. It also requires structured classification rules to ensure high-confidence data collection and accurate evidence gap flagging.

What's the best way to verify content presence and flag evidence gaps during a site audit?

The best way to verify content presence is using a multi-source crawl that cross-references sitemaps, navigation, and full-site crawls. This generates a hierarchical site structure and an evidence manifest to accurately flag any content gaps.

Can I generate a hierarchical site structure manifest for downstream analysis?

Yes, the discovery process generates a structured hierarchical site structure and an evidence manifest. This structured output allows seamless integration of the classified URL inventory into downstream analysis and reporting workflows.