Fetch website content and convert it to plain text using Mozilla Readability.
npx skills add https://github.com/citedy/adclaw --skill site-fetcher
Please help me install this Agent Skill. Skill: Site Fetcher Source: https://github.com/citedy/adclaw/tree/main/src/adclaw/agents/skills/sitefetch Command: npx skills add https://github.com/citedy/adclaw --skill site-fetcher
Fetch entire websites or pages as clean, readable text for AI analysis, enabling better knowledge extraction, benchmarking, and content research.
Run sitefetch with a target URL to produce a single text file containing the site's readable content for analysis.
High-intent search queries and answers about installing and using this skill.
To extract clean text from website content for AI analysis, you can fetch entire sites or specific pages to strip away ads and navigation clutter. The Skill uses Mozilla Readability-based extraction to produce consistent, analysis-ready plain text output, consolidating the results into a single file.
The best way to fetch an entire domain for a content audit is to run a full-site extraction that pulls readable content while stripping boilerplate. It outputs a single text file with page URLs as separators, making the fetched website content easy to review and audit.
Yes, you can selectively target specific sections like docs or blogs when fetching a site by applying glob patterns. This allows you to fetch only relevant website content instead of the entire domain, producing focused plain text for your SEO research or analysis.
Yes, website text extraction removes navigation and ads automatically by using Mozilla Readability-based extraction. This mechanism strips clutter from the fetched pages, ensuring the final output is clean, readable text suitable for competitive analysis and knowledge extraction.
When fetching multiple web pages, the output format is a single text file containing the consolidated readable content. Page URLs are inserted as separators within this file, allowing you to easily identify the source of each extracted text block during your review.
guyruSearch the web via DuckDuckGo HTML and output titles, URLs, and snippets.
bykoleksii-hardoGenerate blog content briefs with keyword research and competitive analysis.
zeronx798Scrape static, dynamic, and protected websites using the scrapling library.
SoborboAnalyze up to five competitor websites to extract marketing data into YAML.
