Skip to main content

Convert Website To Markdown For Rag

Skill Active

Extract clean title, summary, markdown sections, and source metadata from a public documentation page for RAG ingestion.

Purpose

To efficiently transform public documentation web pages into clean, structured markdown data suitable for ingestion into Retrieval Augmented Generation (RAG) systems.

Features

  • Extracts page title, canonical URL, and summary
  • Parses markdown sections with headings
  • Extracts last updated date metadata
  • Provides multiple language SDK examples for integration

Use Cases

  • Preparing website documentation for RAG model training
  • Ingesting technical docs into a knowledge base
  • Automating the conversion of web content for AI processing
  • Extracting structured information from API reference pages

Non-Goals

  • Processing local files or non-publicly accessible URLs
  • Performing complex analysis or summarization beyond data extraction
  • Modifying the content of the website pages

Versioning

  • warning:Release ManagementThere is no explicit versioning in the SKILL.md frontmatter or GitHub releases, and installation instructions reference 'main'.

Installation

First, add the marketplace

/plugin marketplace add iterationlayer/skills
/plugin install skills@iterationlayer-skills

Quality Score

97 /100
Analyzed 1 day ago

Trust Signals

Last commit16 days ago
Stars0
LicenseMIT
Status
View Source

© 2025 SkillRepo · Find the right skill, skip the noise.