skills.rest
Prompt-or-Die-Labs
Prompt-or-Die-LabsOFFICIAL
Explore all skills by this author →
GitHub

knowledge-base-builder

Build elizaOS knowledge bases from domain documents with RAG configuration.

7|2|Updated Nov 9, 2025
Search Tags:#semantic search#embeddings#rag#knowledge base#chunking#elizaos#vector storage
One-click install
npx skills add https://github.com/Prompt-or-Die-Labs/hyper-forge --skill knowledge-base-builder-prompt-or-die-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-base-builder
Source: https://github.com/Prompt-or-Die-Labs/hyper-forge/tree/main/.claude/skills/knowledge-base-builder
Command: npx skills add https://github.com/Prompt-or-Die-Labs/hyper-forge --skill knowledge-base-builder-prompt-or-die-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you turn domain documents into a reliable retrieval layer for elizaOS agents so answers can come from your actual knowledge instead of guesswork.

Core Features & Use Cases

  • Document ingestion and preprocessing: Ingest markdown, PDF, and text with chunking strategies tailored for retrieval quality.
  • Embeddings and semantic retrieval: Generate embeddings and configure vector storage and scoring so queries return relevant memories.
  • Knowledge updates and quality control: Support versioning, updates, and quality metrics to keep the knowledge base accurate over time, such as for agent onboarding to a new domain or improving an agent’s response accuracy with curated procedures and FAQs.

Quick Start

Ask the AI to build an elizaOS knowledge base for your domain using your existing documents and configure semantic search with chunking, embeddings, and retrieval settings.

Frequently Asked Questions about knowledge-base-builder

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

FAQPage Schema
How do I build a RAG knowledge base for elizaOS agents?▼

To build a RAG knowledge base for elizaOS, ingest your domain documents and configure chunking, embeddings, and vector storage settings to create a reliable retrieval layer for accurate agent responses.

What chunking and embedding configurations are needed for semantic search in elizaOS?▼

Semantic search in elizaOS requires configuring the embedding model and dimensions, chunk size and overlap, plus retrieval parameters like topK and minScore to ensure queries return relevant memories.

Can I ingest markdown and PDF documents into an elizaOS vector storage system?▼

Yes, you can ingest markdown, PDF, and text files into elizaOS vector storage using preprocessing and chunking strategies tailored specifically for retrieval quality.

How do I keep my RAG knowledge base accurate during domain updates?▼

Keep your RAG knowledge base accurate during updates by using knowledge versioning and quality metrics to manage ongoing document changes and maintain retrieval performance over time.

What is the best way to improve agent answer accuracy using domain documents?▼

Improve agent answer accuracy by converting domain documents into a curated retrieval layer with configured semantic search, ensuring agents draw answers from actual knowledge instead of guesswork.

Do I need to configure retrieval parameters like topK and minScore for elizaOS knowledge bases?▼

Yes, configuring retrieval parameters like topK and minScore is required for elizaOS knowledge bases to filter and score vector search results effectively for relevant semantic retrieval.

Related Skills

Explore More Software Engineering Skills→
hai-serieshai-series
3

hai-datapipe

Clean text and chunk content into structured pipelines for AI processing.

Official
Intermediate
DexploarerDexploarer
7

knowledge-base-builder

Build elizaOS knowledge bases via document ingestion, embeddings, and semantic retrieval.

Community
Advanced
thecloudtipsthecloudtips
18

Answer Synthesis

Synthesize sourced answers with inline citations and confidence ratings.

Community
Advanced
kevinsweetkevinsweet

vector-hybrid-search

Plan and implement end-to-end vector and hybrid search in Elasticsearch.

Community
Advanced