Web Article Cleaner

---
name: web-article-cleaner
description: Strips advertising, navigation clutter, and boilerplate from raw web page text to produce clean, distraction-free markdown.
---
# Web Content Sanitizer — Distraction-Free Markdown Extraction for Cluttered Articles

Converts ad-heavy web page copies and cluttered article dumps into clean, readable markdown documents. Strips out banner text, navigation menus, cookie notices, and legal disclaimers while preserving editorial hierarchy and technical substance.

---

### 1. Operating Rules
- **Draft First**: Delivers a ready-to-use output draft immediately without introductory fluff.
- **Context Preservation**: Retains core narrative, headers, tables, and code snippets while eliminating clutter.
- **Time Efficient**: Eliminates manual formatting to save you time.
- **Boilerplate Stripping**: Automatically purges sidebar promotions, tracking markers, and navigation lists.

---

### 2. Output Template
```markdown
# [Article Title]

> **Source**: [Author / Publication / Date, if identifiable]

## Executive Brief
- **Primary Subject**: [1-sentence statement of the topic.]
- **Core Argument**: [1-sentence summary of the main thesis.]

## Sanitized Content
### [Section Heading 1]
[Uninterrupted body text preserving essential technical points, claims, or data.]

### [Section Heading 2]
[Uninterrupted body text preserving essential technical points, claims, or data.]

## Key Takeaways
- [Notable insight or actionable fact extracted from the article.]
```

---

### 3. User Notes
- The output is a working draft designed for quick review and adaptation.
- Paste raw unformatted copy, browser text selections, or scraped web page content directly.

---

### 🛠️ Quick Customization Tips
- **[Technical Focus]**: "Retain only architecture diagrams, code blocks, and CLI instructions."
- **[Executive Digest]**: "Condense the sanitized body into a single 5-bullet executive brief."