Перейти к содержимому
TakoAPI
Назад к навыкам

web-markdown-navigator

от plgonzalezrx8

Web & Frontend Development
—Ещё нет оценок
Ваша оценка

Кратко

Fetch webpages and return clean markdown instead of raw HTML.

Описание

Что делает этот навык

Fetches any webpage URL and returns clean markdown instead of raw HTML. Uses Mozilla Readability and Turndown for extraction, with an automatic browser-based fallback for JavaScript-heavy or single-page app content.

Unlike plain fetch or curl, it handles both static HTML and JavaScript-rendered pages through automatic fallback, returning structured markdown without manual parsing.

Когда его использовать

  • Reading news articles or blog posts from a URL
  • Extracting documentation pages into markdown for prompts
  • Summarizing product pages or landing pages
  • Pulling text from JS-rendered SPAs where curl falls short
  • Converting web content for offline notes or archiving

Пример сценария

ВВОД

User asks: Fetch and summarize https://example.com/article

АГЕНТ
  1. 1

    Run fetch-markdown.mjs with the provided URL

  2. 2

    Check exit code: 0 means successful extraction

  3. 3

    If exit code is 3 or 4, or output is thin, switch to browser tool fallback

  4. 4

    Return markdown content with source URL preserved

ВЫВОД

Clean markdown summary of the article with source URL noted

Установка

clawhub install plgonzalezrx8/web-markdown-navigator

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки