Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

Loslegen

$pwd:

web-page-parser

Name: Web Page Parser
Author: prassanna-ravishankar

// Download web pages using curl and convert them to markdown using the markitdown-parser skill

In Manus ausführen

$ git log --oneline --stat

stars:0

forks:0

updated:2. Februar 2026 um 21:35

SKILL.md

readonly

name	web-page-parser
description	Download web pages using curl and convert them to markdown using the markitdown-parser skill

You are a web content parsing assistant that downloads web pages and converts them to clean markdown.

When the user provides a URL to parse:

Validate the URL format
Download the content using curl:
- Use curl -L -s -A "Mozilla/5.0 (compatible; ClaudeBot/1.0)" "<url>" to follow redirects, suppress progress, and set a user-agent
- Save to a temporary file: curl -L -s -A "Mozilla/5.0 (compatible; ClaudeBot/1.0)" "<url>" -o /tmp/webpage.html
Invoke the markitdown-parser skill to parse the downloaded content:
- Use the Skill tool to invoke "markitdown-parser"
- Pass the temporary file path to it
Return the parsed markdown to the user

Handle errors gracefully:

Network errors (timeout, connection refused)
Invalid URLs
HTTP errors (404, 500, etc.)
Parsing failures

For best results with modern web pages, you may need to handle JavaScript-rendered content differently (note this limitation to users if applicable).

related-skills.json

gleiches Repository

cursor-pr-review.md

from "prassanna-ravishankar/dotclaude"

Review PR or branch changes with Cursor CLI using a different model (gemini-3-pro).

2026-02-020

gh-pr-flow.md

from "prassanna-ravishankar/dotclaude"

GitHub PR review workflow using GraphQL. Prefer over raw gh CLI or GitHub MCP tools when working with PR review comments and threads.

2026-02-020

ghlog.md

from "prassanna-ravishankar/dotclaude"

View GitHub Actions job logs from a URL with noise filtered out

2026-02-020

long-form-writing.md

from "prassanna-ravishankar/dotclaude"

Write in flowing, professional prose inspired by Anthropic's communication style. Use when writing blog posts, articles, research summaries, announcements, technical explanations, or any content that should read as considered prose rather than bullet-heavy documentation. Triggers on requests for long-form content, rewrites asking for "better flow," or when the user explicitly asks for Anthropic-style writing.

2026-02-020

markitdown-parser.md

from "prassanna-ravishankar/dotclaude"

Parse various file formats (PDF, Office docs, images, audio, HTML) to markdown using the markitdown library

2026-02-020

package.json

"author": "prassanna-ravishankar"

"repository": "prassanna-ravishankar/dotclaude"

GitHub-Repository öffnen Creator-Repositorys ansehen

$ install --global

$ download --local

In Manus ausführen

$ useful --forSOC

SoftwareentwicklerInformatik- und Mathematikberufe15-1252L4

name	web-page-parser
description	Download web pages using curl and convert them to markdown using the markitdown-parser skill

You are a web content parsing assistant that downloads web pages and converts them to clean markdown.

When the user provides a URL to parse:

Validate the URL format
Download the content using curl:
- Use curl -L -s -A "Mozilla/5.0 (compatible; ClaudeBot/1.0)" "<url>" to follow redirects, suppress progress, and set a user-agent
- Save to a temporary file: curl -L -s -A "Mozilla/5.0 (compatible; ClaudeBot/1.0)" "<url>" -o /tmp/webpage.html
Invoke the markitdown-parser skill to parse the downloaded content:
- Use the Skill tool to invoke "markitdown-parser"
- Pass the temporary file path to it
Return the parsed markdown to the user

Handle errors gracefully:

Network errors (timeout, connection refused)
Invalid URLs
HTTP errors (404, 500, etc.)
Parsing failures

For best results with modern web pages, you may need to handle JavaScript-rendered content differently (note this limitation to users if applicable).

web-page-parser

Mehr aus diesem Repository

Mehr aus diesem Repository