Works with the AI Agents you already use
RAG Knowledge Base Builder
Architect better RAG pipelines with optimized chunking strategies, metadata schemas, and retrieval test cases.
Free
RAG Knowledge Base Builder
Example session with this skill installed
I have about 500 PDF technical manuals for industrial boilers. I need to get them into a Pinecone index for a support bot. How should I structure the data?
- Read your context and instructions
- Compiled the rag knowledge base
I have analyzed your request for industrial boiler manual ingestion. The following strategy focuses on preserving technical specifications and ensuring high-precision retrieval for support engineers.
[RAG Knowledge-Base Builder Report]
📄 Document Assessment & Chunking Strategy:
- Document Type: PDF Technical Manuals (High density of specs and tables)
- Recommended Strategy: Recursive Character Chunking with Markdown Conversion
- Settings: Chunk size: 800 tokens, Overlap: 100 tokens (12.5%)
🏷️ Metadata Schema:
source_file: [String] Original manual filenameequipment_model: [String] Specific boiler model numbersection_type: [String] e.g., Troubleshooting, Installation, Wiringpage_number: [Integer] For source attributionlast_updated: [ISO8601 Date] To prioritize current documentation
🧹 Pre-processing Checklist:
- Convert all PDF tables to Markdown tables to preserve relational data
- Use OCR for wiring diagrams and store descriptions as text
- Strip recurring page headers and company addresses from every page
- Normalize unit measurements (e.g., PSI, Bar) to a consistent format
🔍 Initial Golden Queries (For Testing):
- Simple: "What is the maximum operating pressure for the B-200 series boiler?"
- Complex: "If the error code E04 appears on a 2022 model, what are the primary check steps for the gas valve?"
- Negative: "Who is the CEO of the boiler manufacturing company?"
[Self-Check]
- Chunking strategy explicitly recommended based on document type
- Metadata schema defined for hybrid search
- Pre-processing checklist provided
- Initial golden queries drafted for testing
Next steps
- Implement a Python script using
PyMuPDForUnstructuredto extract text and convert tables to Markdown. - Initialize your Pinecone index with the defined metadata fields as indexed dimensions.
- Run the Golden Queries after the first 10 documents are ingested to verify chunk relevance.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Building a RAG pipeline often fails because developers rush data into a vector database without a strategy. Messy source documents and poor chunking lead to irrelevant search results and high token costs.
What it does
- Analyzes your specific document types to recommend optimal chunking strategies like recursive, semantic, or markdown-aware splitting.
- Defines a strict metadata schema to enable hybrid search and pre-filtering capabilities.
- Generates a targeted pre-processing checklist for cleaning headers, footers, and tables.
- Drafts a "Golden Query" test set to validate retrieval accuracy after ingestion.
Frameworks & tools
Designed for use with LangChain, LlamaIndex, Pinecone, Weaviate, and ChromaDB. Supports PDF, Markdown, and plaintext document processing.
Why this beats prompting it yourself
Generic prompts often miss the nuances of chunk overlap and metadata filtering. This skill applies specific heuristics for token optimization and retrieval precision that go beyond basic text splitting.
Use cases
- Designing a knowledge base for technical documentation repositories.
- Cleaning and structuring messy PDF manuals for an internal support bot.
- Optimizing an existing RAG system that is returning low-quality context chunks.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
Does not perform the actual coding of ingestion scripts or vector database configuration. Requires manual text extraction or OCR for non-text-based documents.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Permissions
No special permissions declared or detected