Saltar al contenido
TakoAPI
Volver a skills

telnyx-rag

por teamtelnyx

Web & Frontend Development
647Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Semantic search and Q&A over workspace files using Telnyx Storage + AI embeddings.

Descripción

Qué hace esta skill

Indexes workspace files into Telnyx Storage with AI-generated embeddings, enabling semantic search and RAG-powered Q&A over memory, knowledge, and skills directories. Files are chunked by document type, synced incrementally, and retrieved with multi-signal reranking before LLM generation.

Uses Telnyx's native embedding, similarity search, and inference APIs in one pipeline, removing the need to wire together a separate vector database, embedding service, and LLM provider.

Cuándo usarla

  • Asking questions about past meeting decisions stored in knowledge files
  • Searching personal notes and preferences by meaning, not keyword
  • Querying documentation for deployment or onboarding steps
  • Auto-syncing workspace memory on a cron schedule for always-current retrieval
  • Retrieving project history from indexed Slack message exports

Flujo de trabajo de ejemplo

ENTRADA

User asks: What is the porting process?

AGENTE
  1. 1

    Runs ./sync.py to upload changed workspace files to Telnyx Storage with smart chunking

  2. 2

    Triggers ./sync.py --embed to generate vector embeddings for uploaded chunks

  3. 3

    Calls ./ask.py with the query, retrieving the top 20 candidate chunks

  4. 4

    Reranks chunks by semantic similarity, keyword overlap, and memory priority

  5. 5

    Calls Telnyx Inference LLM with the top 8 context chunks and returns the answer with source citations

SALIDA

Natural language answer identifying the porting process steps, with references to the source files

Requisitos

  • TELNYX_API_KEY environment variable
  • Telnyx account to generate the API key at portal.telnyx.com

Instalación

clawhub install teamtelnyx/telnyx-rag

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces