AI-powered knowledge management without vector embeddings. Built on Claude Agent SDK, it uses a file system and agent-driven approach. Slower but more reliable. Ideal for operations teams needing accurate, automated knowledge retrieval.
git clone https://github.com/Harryoung/efka.gitAI-powered knowledge management without vector embeddings. Built on Claude Agent SDK, it uses a file system and agent-driven approach. Slower but more reliable. Ideal for operations teams needing accurate, automated knowledge retrieval.
["Prepare your knowledge base: Organize documents in a folder structure (e.g., /operations/supplier_docs/) with clear filenames and update timestamps. Use plain text or markdown for best compatibility.","Define your query: Frame the [QUERY] as a specific operational question (e.g., 'What is the SLA for ticket resolution?'). Avoid vague or overly broad questions.","Specify the folder path: Provide the [FOLDER_PATH] where your knowledge base is stored (e.g., /operations/it_support/). Ensure the AI agent has read access to this directory.","Run the query: Paste the prompt into your AI tool (e.g., Claude, ChatGPT with Agent SDK) and execute. Review the response for accuracy and completeness.","Iterate if needed: If the response is incomplete, refine the query or check the folder path for missing documents. For complex topics, break the query into sub-questions."]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/Harryoung/efkaCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Act as an efka knowledge agent. Given a [QUERY] about [TOPIC], retrieve the most accurate and up-to-date information from the knowledge base stored in [FOLDER_PATH]. If the answer isn't found, respond with 'No relevant information found in the knowledge base.' Do not guess or fabricate details. Focus on operational accuracy.
Query: 'What is the return policy for defective hardware ordered from Supplier X?' Knowledge Base Folder: /operations/supplier_docs/ Response: **Return Policy for Supplier X - Hardware Defects** - **Defective Items:** Must be reported within 14 days of delivery. - **Return Process:** Submit a ticket via the Supplier X portal with the order number and defect description. Include photos of the defect. - **Shipping:** Supplier X provides a prepaid return label for defective items. Customer is responsible for shipping costs for non-defective returns. - **Refund Timeline:** Refunds are processed within 5 business days after the defective item is received and inspected by Supplier X. - **Contact:** For urgent issues, call Supplier X Support at +1 (800) 555-0199 (24/7). *Source: /operations/supplier_docs/supplier_x_returns.md (Last Updated: 2024-05-15)* No additional steps or assumptions were made. The response strictly adheres to the documented policy.
Create and collaborate on interactive animations with powerful, user-friendly tools.
AI assistant built for thoughtful, nuanced conversation
Putting Engineers in the Fast Lane
IronCalc is a spreadsheet engine and ecosystem
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan