skills.rest
team-telnyx
team-telnyxOFFICIAL
Explore all skills by this author →
WebsiteGitHub

telnyx-rag

Index workspace files and answer questions using Telnyx Storage and AI embeddings.

3|2|Updated Feb 10, 2026
Search Tags:#semantic search#rag#knowledge base#ai assistant#telnyx#workspace search
One-click install
npx skills add https://github.com/team-telnyx/telnyx-toolkit --skill telnyx-rag
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: telnyx-rag
Source: https://github.com/team-telnyx/telnyx-toolkit/tree/main/tools/rag
Command: npx skills add https://github.com/team-telnyx/telnyx-toolkit --skill telnyx-rag

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill allows you to semantically search and ask questions about your entire workspace, transforming unstructured data into actionable insights and answers.

Core Features & Use Cases

  • Semantic Search: Find information using natural language queries, going beyond keyword matching.
  • RAG-Powered Q&A: Get direct answers to your questions, with sources cited from your documents.
  • Automated Indexing: Continuously indexes your workspace files (documents, notes, code) for up-to-date knowledge retrieval.
  • Use Case: Ask "What were the key decisions from the Q3 planning meeting?" and get a concise answer with references to the relevant meeting notes.

Quick Start

Ask a question about your workspace by running ./ask.py "What is the porting process?".

Frequently Asked Questions about telnyx-rag

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

FAQPage Schema
How do I set up semantic search over my workspace documents and notes?▼

Semantic search is enabled by indexing your workspace files using Telnyx Storage and AI embeddings. It continuously indexes various file types like markdown and JSON to keep knowledge retrieval up to date.

What is RAG-powered question-answering and how does it cite sources?▼

RAG-powered Q&A generates direct answers to natural language queries by retrieving relevant information from your indexed workspace, citing the specific source documents used to formulate the response.

Can I index large markdown files and JSON documents for natural language retrieval?▼

Yes, the system supports indexing various file types including markdown, JSON, and skill definitions. It applies intelligent chunking for large documents to facilitate accurate natural language retrieval.

How do I ask a question about my indexed knowledge base using the command line?▼

You can ask a question about your knowledge base by running the command ./ask.py followed by your query, such as ./ask.py "What is the porting process?", to retrieve RAG-based answers.

Does semantic search work beyond simple keyword matching for unstructured data?▼

Semantic search finds information using natural language queries, going beyond keyword matching to transform unstructured data into actionable insights and answers from your workspace.

What file types are supported for automated indexing in a workspace knowledge base?▼

Automated indexing supports various file types including markdown, JSON, and skill definitions. The system applies intelligent chunking to handle large documents effectively within the knowledge base.

Related Skills

Explore More Software Engineering Skills→
team-telnyxteam-telnyx
3

telnyx-embeddings

Generate text embeddings and perform semantic search via Telnyx AI APIs.

Official
Intermediate
uw-ssecuw-ssec
25

lumen-ai

Translate natural language data questions into executable SQL queries, visualizations, and insights.

Official
Advanced
TIAN0517TIAN0517

VLM

Analyze images and generate natural language descriptions via image_url or base64 inputs.

Community
Intermediate
malue-aimalue-ai
36

raglite

Index local PDF, Markdown, and plain text documents into structured Markdown for semantic search.

Official
Intermediate