Saltar al contenido
TakoAPI
Volver a skills

web-pilot

por liranudi

Web & Frontend Development
4.7kDescargas según clawskills.sh
1Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Search the web and read page contents without API keys.

Descripción

Qué hace esta skill

Web browsing toolkit built on four Python scripts. Searches via DuckDuckGo, Brave, or Google across multiple pages, reads page text, runs interactive browser sessions with tab management and click support, and downloads files including PDFs. No API keys required.

Works without any API keys or account signups, using Playwright and Chromium directly to access real browser behavior including cookie banner dismissal.

Cuándo usarla

  • Scraping search results from DuckDuckGo without an API key
  • Extracting readable text from a paywalled or cookie-gated page
  • Taking a full-page screenshot of a site for visual reference
  • Downloading a PDF and pulling its text content automatically
  • Navigating a multi-tab session to compare content across pages

Flujo de trabajo de ejemplo

ENTRADA

User asks: find recent articles about LLM context windows and summarize the top result

AGENTE
  1. 1

    Run google_search.py with the query and --pages 2 to get a result list

  2. 2

    Pick the top URL from the returned JSON

  3. 3

    Run read_page.py on that URL with --format markdown

  4. 4

    Parse the markdown output and extract the main article text

  5. 5

    Return a summary to the user

SALIDA

Markdown text of the article, ready for summarization

Instalación

clawhub install liranudi/web-pilot

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

Enlaces