Extract readable web content as text, markdown, or JSON via Trafilatura CLI.
npx skills add https://github.com/cfcosta/duskpi --skill web-fetch-cfcosta
Please help me install this Agent Skill. Skill: web-fetch Source: https://github.com/cfcosta/duskpi/tree/main/skills/web-fetch Command: npx skills add https://github.com/cfcosta/duskpi --skill web-fetch-cfcosta
## What problem does it solve? Fetching web pages to obtain the readable main content is tedious without a browser; this skill provides a lightweight, CLI-based solution to extract clean article text, markdown, or JSON.
## Core Features & Use Cases
### Quick Start Run the CLI against a URL to fetch and output readable content in Markdown or JSON.
High-intent search queries and answers about installing and using this skill.
To extract readable content without browser automation, you can fetch web pages using a packaged Trafilatura CLI to output clean text, markdown, or JSON directly from the URLs.
Fetching article text from multiple URLs is handled by processing each link through the Trafilatura CLI, which isolates readable content and formats it as markdown or JSON for archiving.
Yes, you can output extracted web content as JSON. The skill processes URLs using the Trafilatura CLI to produce structured JSON data suitable for downstream workflows.
Yes, content extraction requires a fixed FETCHCLI path where the packaged Trafilatura CLI is located, and the system verifies the CLI is executable before use.
Web content extraction works for generating summaries without a browser by using the Trafilatura CLI to fetch pages and return clean text or markdown for summary workflows.
onymchatConfigure App Clip targets, invocation URLs, and data sharing for iOS apps.
quanpersie2001Process multimodal media to extract text, transcriptions, and structured data.
uhvc7652Converts JSON, CSV, YAML, and XML formatsUTE and parses JSON strings with JSONPath for targeted extraction.
zeronx798Scrape static, dynamic, and protected websites using the scrapling library.
