content-retrieval

Extract content from files using markdown headings and frontmatter metadata.

Updated Jan 23, 2026

Search Tags:#markdown #grep #frontmatter #token-efficiency #section-extraction #knowledge-discovery #content-retrieval

Ready to run

npx skills add https://github.com/alexsandrocruz/DominusLeads --skill content-retrieval-alexsandrocruz

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: content-retrieval
Source: https://github.com/alexsandrocruz/DominusLeads/tree/main/backend/Sapienza.Leads/.claude/skills/content-retrieval
Command: npx skills add https://github.com/alexsandrocruz/DominusLeads --skill content-retrieval-alexsandrocruz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of reading large documents by extracting only the necessary portions through Markdown headings and frontmatter, reducing processing time and token usage.

Core Features & Use Cases

Section-based extraction: locate content by headings and separators to minimize full-file reads.
Depth-level retrieval: supports L0-L5 retrieval strategies for exists, count, lookup, overview, section, and full reads.
Frontmatter-driven indexing: leverages YAML metadata to quickly identify relevant content and context.
Use Case: summarize a knowledge base, perform fast lookups, or extract specific sections from code repositories.

Quick Start

Use the content-retrieval skill to read the Summary section from a document by locating the "## Summary" heading and reading content up to the next delimiter.

Frequently Asked Questions about content-retrieval

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

FAQPage Schema

How do I extract a specific section from a large markdown document without reading the entire file?▼

Section-based content retrieval locates specific markdown headings and reads content up to the next delimiter, minimizing full-file reads and reducing token usage.

What is frontmatter-driven content retrieval and how does it work?▼

Frontmatter-driven content retrieval leverages YAML metadata to quickly identify relevant content and context within knowledge bases, enabling fast lookups without scanning entire documents.

Can I retrieve only the metadata from a markdown file instead of the full content?▼

Yes, frontmatter metadata extraction isolates YAML headers from markdown files, allowing you to index and retrieve document context without loading the body content.

What is the best way to control retrieval depth when querying documentation pipelines?▼

Depth-level retrieval supports L0-L5 strategies for exists, count, lookup, overview, section, and full reads, giving you granular control over how much content is extracted from documentation pipelines.

Why does reading large markdown files consume so many tokens during knowledge discovery?▼

Full-file reads transfer unnecessary content across the entire document. Token-efficient content retrieval solves this by reading only necessary sections through markdown headings and frontmatter, minimizing data transfer.

Does content retrieval work with code repositories for targeted data extraction?▼

Yes, content retrieval applies to code repositories where partial reads yield quick insights, summaries, or targeted data extraction by leveraging markdown headings and frontmatter structure.