Install
Quick install
npx skills add https://github.com/michalparkola/tapestry-skills-for-claude-code/tree/main/article-extractornpx skills add michalparkola/tapestry-skills-for-claude-code --skill article-extractor --agent claude-codenpx skills add michalparkola/tapestry-skills-for-claude-code --skill article-extractor --agent cursornpx skills add michalparkola/tapestry-skills-for-claude-code --skill article-extractor --agent codexnpx skills add michalparkola/tapestry-skills-for-claude-code --skill article-extractor --agent opencodenpx skills add michalparkola/tapestry-skills-for-claude-code --skill article-extractor --agent github-copilotnpx skills add michalparkola/tapestry-skills-for-claude-code --skill article-extractor --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add michalparkola/tapestry-skills-for-claude-code --skill article-extractorManual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/michalparkola/tapestry-skills-for-claude-code.gitcp -r tapestry-skills-for-claude-code/article-extractor ~/.claude/skills/article-extractor
Extract full article text and metadata from web pages
What is it?
A Claude Code skill for extracting full article text and metadata from web pages. It strips away navigation, ads, sidebars, and other non-content elements to deliver clean, readable article text. Ideal for content research, archiving, and building knowledge bases from web sources.
How to use it?
When you provide a URL, the skill automatically fetches the web page, identifies the main article content, and extracts clean text along with metadata such as title, author, publish date, and description. It handles various website layouts and content management systems.The extracted content can be used for research, summarization, or further processing within your Claude workflow.
Key Features
- Clean text extraction from web articles, removing ads, navigation, and clutter
- Metadata extraction including title, author, date, and description
- Handles various website layouts and CMS platforms
- Integrates with other Tapestry skills for content processing pipelines
- Preserves article structure and formattingView on GitHub
GitHub Stats
StarsForksLast UpdateAuthormichalparkolaLicenseMITVersion1.0.0Categories
CommunicationTags
webdocument-processingcodingwritingvideoFeatures
Related Skills
More from CommunicationNotebookLM Integration
Lets Claude Code chat directly with NotebookLM for source-grounded answers based exclusively on uploaded documents3.5kPleasePromptoProductivityCommunication00
Internal Communications
Write internal communications like status reports, newsletters, and FAQs5.3kAnthropicProductivityCommunication00
Slack GIF Creator
Create animated GIFs optimized for Slack's size constraints5.3kAnthropicCreativeCommunication00
---
Source: https://github.com/michalparkola/tapestry-skills-for-claude-code/tree/main/article-extractor
Author: michalparkola
License: https://opensource.org/licenses/MIT
GitHub Stars: 237
Tags: web, document-processing, coding, writing, video
SKILL.md source
--- name: article-extractor description: Extract full article text and metadata from web pages --- # article-extractor Extract full article text and metadata from web pages What is it? A Claude Code skill for extracting full article text and metadata from web pages. It strips away navigation, ads, sidebars, and other non-content elements to deliver clean, readable article text. Ideal for content research, archiving, and building knowledge bases from web sources. ## How to use it? When you provide a URL, the skill automatically fetches the web page, identifies the main article content, and extracts clean text along with metadata such as title, author, publish date, and description. It handles various website layouts and content management systems. The extracted content can be used for research, summarization, or further processing within your Claude workflow. ## Key Features * Clean text extraction from web articles, removing ads, navigation, and clutter * Metadata extraction including title, author, date, and description * Handles various website layouts and CMS platforms * Integrates with other Tapestry skills for content processing pipelines * Preserves article structure and formattingView on GitHub ### GitHub Stats StarsForksLast UpdateAuthormichalparkolaLicenseMITVersion1.0.0 ### Categories Communication ### Tags webdocument-processingcodingwritingvideo ### Features ## Related Skills More from Communication ### NotebookLM Integration Lets Claude Code chat directly with NotebookLM for source-grounded answers based exclusively on uploaded documents 3.5kPleasePromptoProductivityCommunication00 ### Internal Communications Write internal communications like status reports, newsletters, and FAQs 5.3kAnthropicProductivityCommunication00 ### Slack GIF Creator Create animated GIFs optimized for Slack's size constraints 5.3kAnthropicCreativeCommunication00 --- **Source**: https://github.com/michalparkola/tapestry-skills-for-claude-code/tree/main/article-extractor **Author**: michalparkola **License**: https://opensource.org/licenses/MIT **GitHub Stars**: 237 **Tags**: web, document-processing, coding, writing, video
Related skills 6
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
clarify
Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.
WordPress / wp-performance
Profiling, caching, database optimization, Server-Timing
Typefully / typefully
Create, schedule, and publish social media content across X, LinkedIn, Threads, Bluesky, and Mastodon
WordPress / wp-abilities-api
Capability-based permissions and REST API authentication
Hugging Face / hugging-face-jobs
Run compute jobs and Python scripts on HF infrastructure