Saltar al contenido
TakoAPI
Volver a skills

hk101-living-rag

por metatronsdoob369

Search & Research
758Descargas según clawskills.sh
2Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Simple RAG over local text/markdown.

Descripción

Qué hace esta skill

Runs retrieval-augmented generation over a local folder of text or markdown files. Given a query, it finds the most relevant document chunks and returns a synthesized answer with source snippets.

Keeps documents local and avoids uploading sensitive content to external search or indexing services.

Cuándo usarla

  • Querying a local knowledge base without a cloud service
  • Searching project documentation by natural language
  • Answering questions from a folder of meeting notes
  • Looking up policies stored as markdown files
  • Finding relevant content across a large docs directory

Flujo de trabajo de ejemplo

ENTRADA

User asks: 'What is our refund policy?' with docsPath set to ./company-docs

AGENTE
  1. 1

    Scans the target folder for text and markdown files

  2. 2

    Chunks documents into searchable segments

  3. 3

    Embeds the query and document chunks using OpenAI

  4. 4

    Retrieves the top k matching chunks by similarity score

  5. 5

    Synthesizes an answer from the matched content

SALIDA

A direct answer to the query plus an array of matches with file path, score, and snippet for each

Requisitos

  • OPENAI_API_KEY environment variable

Instalación

clawhub install metatronsdoob369/hk101-living-rag

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

Enlaces