kb-retriever

Search local knowledge directories for answers using hierarchical indexes and progressive retrieval.

1|Updated Aug 16, 2023
One-click install
npx skills add https://github.com/monlor/dotfiles --skill kb-retriever-monlor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kb-retriever
Source: https://github.com/monlor/dotfiles/tree/main/config/ai/agents/skills/kb-retriever
Command: npx skills add https://github.com/monlor/dotfiles --skill kb-retriever-monlor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires grep, read_file, pdftotext, pdfplumber, pandas, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines AI agents' ability to answer questions based on a local, multi-format knowledge directory, eliminating the need for loading entire files into context.

Core Features & Use Cases

  • Multi-format Support: Works with Markdown, PDF, Excel, and more, adaptable for various file types.
  • Hierarchical Indexing: Navigates through a hierarchical index structure in data_structure.md for precise searches.
  • Progressive Retrieval: Uses grep and selective file reading to efficiently search for answers without overwhelming context.
  • Use Case: Retrieve specific information from a complex knowledge directory stored on local storage, allowing for more efficient decision-making and knowledge utilization.

Quick Start

Load your local knowledge base and activate the skill 'kb-retriever'. Then ask your AI, "Provide information from the knowledge base on topic 'Project Management'."

Frequently Asked Questions about kb-retriever

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

FAQPage Schema
How do I search a local knowledge base without loading full PDF and Markdown files into context?

Search a local knowledge base without loading full files by using progressive retrieval to navigate a hierarchical index in data_structure.md, then selectively reading specific data structures to find precise answers efficiently.

Can AI agents retrieve specific information from mixed file formats like PDF and Excel?

AI agents can retrieve specific information from mixed formats like PDF and Excel by applying file and tool-specific reading strategies, adapting processing logic for each format without overwhelming the context window.

What is hierarchical indexing for local data indexing and how does it work?

Hierarchical indexing for local data indexing works by mapping a structured knowledge directory into a data_structure.md file, allowing searches to progressively navigate the hierarchy to locate exact answers without scanning entire documents.

Does progressive retrieval work with grep and selective file reading for local directories?

Progressive retrieval works with grep and selective file reading by first searching the hierarchical index structure, then using targeted tool-specific strategies to extract exact answers from local directories efficiently.

What are the limitations of using hierarchical indexing for complex knowledge directories?

A limitation of hierarchical indexing for complex knowledge directories is the requirement for a structured data_structure.md file, meaning unstructured local data must be pre-processed and indexed before progressive retrieval can function.