rag-skill

Retrieve information from local file systems using grep and pandas-based processing.

1|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/raybird/telenexus --skill rag-skill-raybird
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rag-skill
Source: https://github.com/raybird/telenexus/tree/main/skills/rag-skill
Command: npx skills add https://github.com/raybird/telenexus --skill rag-skill-raybird

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdf2image, pandas, openpyxl, pypdf, pdfplumber, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of navigating and extracting precise information from large, unstructured local document repositories without relying on external cloud-based vector databases.

Core Features & Use Cases

  • Hierarchical Navigation: Uses data_structure.md files to intelligently map and locate information across complex directory trees.
  • Just-in-Time Learning: Enforces a mandatory reading of technical references before processing complex formats like PDF or Excel to ensure optimal tool usage.
  • Iterative Retrieval: Employs a multi-round search strategy that refines queries based on initial findings to ensure high-accuracy results.

Quick Start

Ask the agent to search your local knowledge directory for specific information regarding a project or topic by providing the relevant keywords.

Frequently Asked Questions about rag-skill

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

FAQPage Schema
How do I search a local knowledge base for specific information in PDF and Excel files?

You can search a local knowledge base by providing keywords to the agent, which then navigates hierarchical directory structures and applies format-specific extraction strategies to retrieve targeted information from PDF and Excel files.

What is the best way to extract text from complex PDF documents offline?

The best way to extract text from complex PDFs offline is using a multi-round iterative retrieval strategy that applies format-specific parsing via pdfplumber and pypdf, ensuring high-accuracy results without relying on external cloud-based vector databases.

Does this local knowledge retrieval approach require an external cloud-based vector database?

No, this local knowledge retrieval approach is privacy-focused and offline-first, meaning it does not require an external cloud-based vector database to parse PDF text or aggregate Excel data for research tasks.

How do I aggregate Excel data for research tasks without uploading files to the cloud?

You can aggregate Excel data offline using pandas-based processing and openpyxl, which applies format-specific extraction strategies to local file systems, satisfying privacy-focused research requirements without uploading files to the cloud.

Can I navigate complex directory trees to locate specific project documentation?

Yes, you can navigate complex directory trees by using data_structure.md files to intelligently map and locate specific project documentation across hierarchical local file systems before applying format-specific extraction.

What are the limitations of offline-first knowledge management for unstructured document repositories?

Limitations of offline-first knowledge management include the need to enforce mandatory reading of technical references before processing complex formats like PDF or Excel, and it requires local dependencies such as pdf2image, pandas, and pypdf to function.