web-scrapelisted

Fetch a web page to clean markdown locally via Crawl4AI — no external API, no per-request cost, content never leaves the device. Triggers on: 'scrape <url>', 'get the text/content of this page', 'read this website', 'extract the article', after read-router picks a normal or anti-bot web page. Default for ~90% of pages. Use --stealth for anti-bot/login/heavy-JS sites. Firecrawl (external) is only a last-resort fallback for the rare page local can't crack.
juliuswiener/nord-kit · ★ 0 · AI & Automation · score 65

Install: claude install-skill juliuswiener/nord-kit

# web-scrape — local-first page → markdown Pulls a URL to clean markdown with Crawl4AI running on this machine. Free, no API key, the page content never leaves the device. This is the default reader for normal web pages. Tool entrypoint (dispatcher over the local venv): ```bash bash "$CLAUDE_PLUGIN_ROOT/bin/nw" scrape <url> # plain → auto-escalates to stealth if blocked bash "$CLAUDE_PLUGIN_ROOT/bin/nw" scrape <url> --stealth # force stealth (skip plain): known anti-bot/login bash "$CLAUDE_PLUGIN_ROOT/bin/nw" scrape <url> --no-escalate # plain only, never retry stealth bash "$CLAUDE_PLUGIN_ROOT/bin/nw" scrape <url> --out page.md # write to file instead of stdout bash "$CLAUDE_PLUGIN_ROOT/bin/nw" scrape <url> --raw # full markdown (default = pruned main content) ``` ## Escalation ladder (auto — cheapest rung that works) ``` 1. nw scrape <url> ← plain Crawl4AI, free, ~90% of pages └─ result empty or a bot-wall ("just a moment", "enable JavaScript", captcha, cloudflare…)? 2. → AUTO-retries once with --stealth ← invisible_playwright patched Firefox, on-device 3. STILL blocked + non-sensitive? ← only then consider Firecrawl MCP (external, credits) 4. sensitive material? ← stays at rung 2. Never send it to an external API. ``` `nw scrape` does rungs 1→2 automatically: plain first, and only if the result looks blocked/empty does it fetch again with stealth. So **just call `scrape`** — you don't decide per