Sponsor Suno AI Music arrow_forward
Skill

Article Extractor

Extract full article text and metadata from web pages

Type
Skill
GitHub stars
550
License
MIT
Repo last updated
Mar 11, 2026
Source file
README.md

What Article Extractor is

Article Extractor is a skill published in the michalparkola/tapestry-skills repository on GitHub, which has about 550 stars. The repository describes itself as: “Claude Code skills to download sources (articles, PDFs, YouTube video transcripts)”

A skill is a folder with a SKILL.md file: frontmatter with a name and a description, followed by instructions Claude follows. Claude loads a skill automatically when a task matches its description, and you can also run it directly with a slash and its name.

Skills work in Claude Code and in Claude Cowork, which makes Article Extractor a portable way to give Claude the same method everywhere.

How to install Article Extractor

Claude Code

  1. Download the article-extractor folder from the repository.
  2. Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project.
  3. Claude loads it automatically when a task matches; you can also run it with / and its name.

Claude Cowork

  1. Zip the skill folder so SKILL.md sits at the top level of the folder.
  2. Open Customize → Skills, click +, then upload the ZIP.
  3. Start a task that matches the description, or call it by name with /.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from README.md, shared under the repository's MIT license. Read the full file on GitHub.

A collection of productivity skills for AI agents like Claude Code that help you work faster and learn better.

Are you a founder of a tech company? Check out Tapestry – the AI planning partner that helps everyone on your team make better decisions faster.

Skills Included

0. Learn This ⭐

The unified workflow that orchestrates everything. Just say learn-this and it:

  1. Detects content type (YouTube, article, PDF)
  2. Extracts clean content
  3. Automatically creates a Ship-Learn-Next action plan

One command. Complete workflow. From learning to shipping.

1. YouTube Transcript Downloader

Download and clean YouTube video transcripts with automatic deduplication and readable formatting.

Features:

  • Downloads transcripts using yt-dlp
  • Removes duplicate lines (YouTube VTT format issue)
  • Uses video title for filename
  • Fallback to Whisper transcription if no subtitles available
  • Automatic cleanup of temporary files

Use cases:

  • Get transcripts from educational videos
  • Extract content from tutorials
  • Archive important talks/interviews

2. Article Extractor

Extract clean, readable content from web articles and blog posts, removing ads, navigation, and clutter.

Features:

  • Uses Mozilla Readability or trafilatura for extraction
  • Removes ads, navigation, and newsletter signups
  • Saves as clean plain text
  • Uses article title for filename
  • Multiple extraction methods with automatic fallback

Use cases:

  • Save articles for offline reading
  • Extract tutorial content
  • Archive important blog posts
  • Get clean text without distractions

3. Scrum Sage

AI-powered Scrum Master and Enterprise Agility Coach based on Jeff Sutherland, Taiichi Ohno, and First Principles thinking.

Features:

  • Sprint analysis (basic and expert modes)
  • Backlog refinement and story sizing guidance
  • Anti-pattern detection and impediment radar
  • Flow efficiency and cognitive load analysis
  • Scrum@Scale advice for growing organizations
  • Retrospective synthesis and predictive modeling

Use cases:

  • Get coaching on Scrum mechanics, ceremonies, and artifacts
  • Analyze sprint health, velocity trends, and predictability
  • Remove impediments and detect systemic bottlenecks
  • Plan scaling strategy (with Scrum@Scale, not SAFe)
  • Facilitate retrospectives and backlog refinement
  • Optimize team dynamics and sustainable pace

4. Session Log

Summarize your Claude Code conversation and append it to a weekly agent-log file.

Features:

  • Reverse chronological daily entries
  • Automatic ISO week file naming (YYYY-wWW agent-log.md)
  • CHUNK markers for reusable outputs (plans, summaries, frameworks)
  • Appends without overwriting existing entries
  • Multi-day session support with date attribution

Use cases:

  • Log what you accomplished in a session
  • Build a searchable weekly work journal
  • Track decisions, outputs, and topics across sessions

5. Unblock Action

Get unstuck on vague or overwhelming tasks. Clarifies the intended output, scopes it to today, and identifies the concrete next physical action.

Features:

  • Socratic but fast — 2-3 questions max
  • Turns fuzzy goals into concrete deliverables
  • Scopes multi-day projects to today's completable slice
  • Outputs a clean action card with deliverable, scope, and next step

Use cases:

  • "I need to work on marketing but can't start"
  • "I'm stuck on pricing"
  • "I have to do something about onboarding"
  • Any vague task you keep avoiding

6. Ship-Learn-Next Action Planner

Transform passive learning content (transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework.

Features:

  • Converts advice into concrete, shippable iterations (reps)
  • Creates 5-rep action plans with timelines
  • Focuses on DOING over studying
  • Includes reflection questions after each rep
  • Saves plan to markdown file

Use cases:

  • Turn YouTube tutorials into action plans
  • Extract implementation steps from articles

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Article Extractor?

Article Extractor is a skill for Claude Code and Claude Cowork from the michalparkola/tapestry-skills repository on GitHub. Extract full article text and metadata from web pages

How do I install Article Extractor in Claude Code?

Download the article-extractor folder from the repository. Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project. Claude loads it automatically when a task matches; you can also run it with / and its name.

Can I use Article Extractor in Claude Cowork?

Zip the skill folder so SKILL.md sits at the top level of the folder. Open Customize → Skills, click +, then upload the ZIP. Start a task that matches the description, or call it by name with /.

Is Article Extractor safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.