web-scrape
Extract Clean Web Content
Web pages often include navigation, ads, and dynamic content that obscure useful information. This skill guides Claude, Codex, or Claude Code to capture pages and return clean content.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "web-scrape" from https://skillstore.io/skills/21pounder-web-scrape.md and its manifest at https://skillstore.io/api/skills/21pounder-web-scrape/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "web-scrape". Scrape a public news article in markdown.
Expected outcome:
A clean article with title, source URL, date, author, headings, and body content without navigation or ads.
Using "web-scrape". Scrape a public product page as structured content.
Expected outcome:
- Product name
- Price and availability
- Description
- Key features
- Specifications
- Source URL
Using "web-scrape". Scrape a page with infinite scroll and save a screenshot.
Expected outcome:
A content summary, the screenshot filename, and notes about sections that loaded after scrolling.
Security Audit
SafeAll 46 static findings are false positives after context review. The external-command matches are Markdown formatting or Cheerio selector calls, and the network matches are examples or placeholders. No prompt injection, data exfiltration intent, or malicious business logic was found in the reviewed files.
Risk Factors
⚙️ External commands (42)
🌐 Network access (4)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/21pounder-web-scrape/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/21pounder-web-scrape?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/21pounder-web-scrape?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/21pounder-web-scrape/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/21pounder-web-scrape.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
21pounder. (2026). web-scrape security audit report (audit version 8) [Author version 3.0.0]. Skillstore. https://skillstore.io/skills/21pounder-web-scrape/audits/8BibTeX citation
@techreport{21pounder-21pounder-web-scrape-2026,
author = {21pounder},
title = {web-scrape security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/21pounder-web-scrape/audits/8},
note = {Author version 3.0.0}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "web-scrape security audit report (audit version 8)"
version: "3.0.0"
type: report
authors:
- name: "21pounder"
date-released: "2026-07-04"
url: "https://skillstore.io/skills/21pounder-web-scrape/audits/8"
identifiers:
- type: other
value: "skillstore:21pounder-web-scrape:audit:8"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Research Article Extraction
Capture a readable article with title, source, author, date, and body content.
Product Page Review
Extract prices, availability, descriptions, and specifications from public product pages.
Documentation Capture
Preserve headings, lists, and code-oriented structure from public documentation pages.
Try These Prompts
Use web-scrape on [URL] and return clean markdown with title, source, author, date, and main content.
Use web-scrape on [product URL] with JSON output. Include price, availability, description, and specifications when visible.
Use web-scrape on [URL] with scroll and screenshot. Summarize the main content and mention blocked sections.
Use web-scrape on [first page URL]. Detect pagination, ask before scraping all pages, then combine the article in order.
Best Practices
- Use the simplest output format that fits the next task.
- Ask for permission before scraping multi-page, authenticated, or sensitive content.
- Close the browser after every scrape, even when navigation fails.
Avoid
- Do not use it to bypass CAPTCHA, paywalls, robots rules, or access controls.
- Do not capture authenticated pages unless the user clearly authorizes the session.
- Do not return raw DOM dumps when the user asked for readable content.
Frequently Asked Questions
What does this skill scrape?
Does it require Playwright?
Can it scrape dynamic pages?
Can it bypass blocked content?
What formats are supported?
Is it suitable for private pages?
Developer Details
Author
21pounderLicense
MIT
Author version
v3.0.0
Skillstore revision
r1
Repository
https://github.com/21pounder/terminalAgent/tree/main/deepresearch/.claude/skills/web-scrapeRef
e9e4712298ed071d92417a41714be123eb8364fa
Maintenance freshness
7/18/2026
Usage
47 downloads · 213 views
File structure