skills.rest
marmikcfc
marmikcfcCOMMUNITY
Explore all skills by this author →
GitHub

site-content-catalog

Catalog website pages and metadata into a markdown content table.

Updated Apr 19, 2026
Search Tags:#audit#content#catalog#metadata#website#sitemap#mapping
One-click install
npx skills add https://github.com/marmikcfc/pepper-skills --skill site-content-catalog-marmikcfc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: site-content-catalog
Source: https://github.com/marmikcfc/pepper-skills/tree/main/skills/site-content-catalog
Command: npx skills add https://github.com/marmikcfc/pepper-skills --skill site-content-catalog-marmikcfc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Catalogs all website pages and metadata (URLs, titles, topics, and content types) for audits.

Core Features & Use Cases

  • Crawl and catalog website content: collect URLs, titles, topics, and content types to support audits and content maps.
  • Build a centralized content catalog: produce a markdown table with per-page metadata and word counts for governance and optimization.
  • Save and share results: deliver a stateful catalog at seo/content-catalog.md for downstream SEO and brand-voice tasks.

Quick Start

Ask your agent to crawl the target website and generate a content catalog with URLs, titles, topics, and content types.

Frequently Asked Questions about site-content-catalog

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

FAQPage Schema
How do I catalog all website pages and metadata for a content audit?▼

A website content catalog is a centralized inventory mapping all site pages and metadata, including URLs, titles, topics, and content types. It is used to support content audits, governance, and gap analyses across a website.

What is the best way to inventory website content and build a content map?▼

Building a content map involves crawling a website to collect URLs, titles, topics, and content types, then saving the results as a markdown table. This stateful catalog supports downstream SEO tasks and brand-voice optimization.

Do I need sitemap data to perform a website content gap analysis?▼

Yes, sitemap data is required to catalog website content and perform gap analyses. The sitemap provides the foundational list of URLs needed to crawl the site and extract metadata for the content inventory.

Can I save and share website audit results for downstream SEO tasks?▼

Yes, catalog results are saved as a stateful markdown file at seo/content-catalog.md. This file contains the extracted per-page metadata and word counts, making it easy to share for downstream SEO and brand-voice tasks.

Does cataloging website metadata require access to Claude via HTTP APIs?▼

Yes, persisting the website content catalog requires access to Claude via HTTP APIs. This access allows the agent to crawl the target website and save the stateful catalog file for downstream tasks.

Related Skills

Explore More Content & Communication Skills→
vibecodevibecode
1

SupaData

Extract transcripts, metadata, and structured data from videos and websites.

Official
Intermediate
KhaledaunKhaledaun

content-creator

Generate SEO-optimized marketing content with consistent brand voice using Python scripts.

Community
Intermediate
ginkidaginkida
20

pdf-reader

Extract text, tables, and metadata from PDF documents.

Community
Advanced
billydeeii136billydeeii136

seo-audit

Audit website SEO with subagents for technical, content, and on-page analysis.

Community
Advanced