skills.rest
agencia-conversion
agencia-conversionOFFICIAL
Explore all skills by this author →
WebsiteGitHub

content-import

Bulk-import website pages from sitemaps into project contents directories.

49|7|Updated May 4, 2026
Search Tags:#sitemap#content import#markdown frontmatter#editorial workflow#web extraction#idempotent writing#seo research
One-click install
npx skills add https://github.com/agencia-conversion/agentic-seo-skills --skill content-import
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: content-import
Source: https://github.com/agencia-conversion/agentic-seo-skills/tree/main/skills/content-import
Command: npx skills add https://github.com/agencia-conversion/agentic-seo-skills --skill content-import

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you bulk-import already-published content from a website so you can start editorial work without manually copying pages or recreating metadata.

Core Features & Use Cases

  • Sitemap discovery and URL classification: Reads the target site’s sitemap and maps URLs into your project/contents/<origin>/<slug>.md structure.
  • Deterministic extraction with traceability: Extracts titles, bodies, dates, bylines, and writes imported pages with an evidence-friendly import block.
  • Idempotent, editorial-safe materialization: Avoids overwriting substantive existing content and preserves the required canonical frontmatter contract (contract_version: 1, clusters: []).

Quick Start

Import content from a site’s sitemap into project/contents by running the content-import skill with your site URL as the base and letting it extract and materialize each eligible page.

Frequently Asked Questions about content-import

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

FAQPage Schema
How do I bulk import existing website content using a sitemap?▼

To bulk import content, the skill reads a target site's sitemap to map URLs into origin buckets, extracts page data, and writes each page as a markdown file with canonical frontmatter into your contents directory.

Can I backfill competitor blog content without overwriting my existing markdown files?▼

Yes, the import mechanism is idempotent and editorial-safe, meaning it preserves the canonical frontmatter contract and avoids overwriting any substantive existing content when backfilling competitor site pages.

Does content extraction preserve markdown frontmatter for editorial workflows?▼

Yes, extraction writes imported pages with an evidence-friendly import block and preserves canonical frontmatter fields like `contract_version: 1` and empty clusters for downstream editorial workflows.

What is the best way to mirror a partner site's blog for SEO research?▼

Sitemap-based mirroring parses a partner site's URL structure, classifies links into origin buckets, and extracts titles, bodies, and bylines into a structured markdown directory for SEO research.

How does sitemap parsing classify URLs into origin buckets?▼

Sitemap parsing classifies URLs into origin buckets by reading the target site's sitemap and mapping each extracted link into a structured `project/contents/<origin>/<slug>.md` directory for editorial clustering.

Related Skills

Explore More Content & Communication Skills→
MarkusonMarkuson

bmad-index-docs

Generate or update an index.md file with categorized file and subdirectory listings.

Community
Basic
marcromeynmarcromeyn
3

obsidian-vault-ops

Read, write, and manage files inside an Obsidian vault.

Community
Basic
avvaleavvale

commit-pr

Commit changes, push to a feature branch, and create a GitHub Pull Request.

Official
Advanced
Executioner1939Executioner1939
8

scrape-firecrawl

Crawl documentation sites via Firecrawl and store pages as markdown with manifests.

Community
Intermediate