Saltar al contenido
TakoAPI
Volver a skills

desearch-crawl

por okradze

Web & Frontend Development
553Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Crawl/scrape and extract content from any webpage URL.

Descripción

Qué hace esta skill

Crawls a webpage by URL and returns its content as clean text or raw HTML. Powered by the Desearch API. Useful when an agent needs to read the full contents of a specific page rather than search for it.

Returns clean, markup-free text by default, which keeps agent context lean compared to raw HTML scrapers.

Cuándo usarla

  • Reading a documentation page before writing code
  • Extracting article text for summarization
  • Fetching a competitor's pricing page for comparison
  • Pulling release notes from a changelog URL
  • Checking the current content of a web page before editing

Flujo de trabajo de ejemplo

ENTRADA

User asks: summarize the Python 3 tutorial index

AGENTE
  1. 1

    Call crawl with 'https://docs.python.org/3/tutorial/index.html' and default text format

  2. 2

    Receive plain text content of the page

  3. 3

    Parse section headings and descriptions from the text

  4. 4

    Compose a summary from the extracted content

SALIDA

A structured summary of the Python 3 tutorial sections

Requisitos

  • DESEARCH_API_KEY environment variable
  • Desearch account at console.desearch.ai (paid balance required)

Instalación

clawhub install okradze/desearch-crawl

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

Enlaces