How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

Web Scraper (r.jina.ai) - Skill

Name: Web Scraper (r.jina.ai)
Author: bighardperson

Imported from bighardperson/computer-science-skills-collection (skills/web-scraper-jina/SKILL.md). Install upstream with npx skills add bighardperson/computer-science-skills-collection --skill web-scraper-jina. Copyright stays with the author.

Web Scraper using r.jina.ai

Bypass Cloudflare and scrape any website using free r.jina.ai API.

Features

Bypass Cloudflare, Turnstile, and other protections
Works on Truth Social, Bitget, and other protected sites
Returns clean Markdown content
Free to use

Usage

Simply prepend https://r.jina.ai/ to any URL:

https://r.jina.ai/https://truthsocial.com/@realDonaldTrump
https://r.jina.ai/https://bitget.com/events/poolx

Examples

Get Trump Truth Social posts:

curl -s "https://r.jina.ai/https://truthsocial.com/@realDonaldTrump"

Get any protected page:

curl -s "https://r.jina.ai/https://example.com"

In Code

import requests

def scrape(url):
    return requests.get(f"https://r.jina.ai/{url}").text

Use Cases

Scrape Truth Social, Gab, Gettr
Bypass Cloudflare protected sites
Extract content from news articles
Monitor competitors

Install Web Scraper (r.jina.ai) and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "bighardperson-computer-science-skills-collection-web-scr-13375a", "kind": "skill", "name": "Web Scraper (r.jina.ai)", "description": "Bypass Cloudflare and scrape any website using r.jina.ai API. Works on sites with strong protection like Truth Social, Cloudflare Turnstile, etc.", "publisher": "bighardperson", "version": "1.0.0", "capabilities": { "domains": [ "coding" ], "tags": [ "skill-md", "web", "scraper", "cloudflare", "bypass", "jina", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Bypass Cloudflare and scrape any website using r.jina.ai API. Works on sites with strong protection like Truth Social, Cloudflare Turnstile, etc." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/bighardperson/computer-science-skills-collection", "path": "skills/web-scraper-jina/SKILL.md", "ref": "HEAD", "url": "https://github.com/bighardperson/computer-science-skills-collection/blob/HEAD/skills/web-scraper-jina/SKILL.md", "key": "bighardperson/computer-science-skills-collection/skills/web-scraper-jina/SKILL.md" } }, "instructions": "# Web Scraper using r.jina.ai\n\nBypass Cloudflare and scrape any website using free r.jina.ai API.\n\n## Features\n\n- Bypass Cloudflare, Turnstile, and other protections\n- Works on Truth Social, Bitget, and other protected sites\n- Returns clean Markdown content\n- Free to use\n\n## Usage\n\nSimply prepend `https://r.jina.ai/` to any URL:\n\n```\nhttps://r.jina.ai/https://truthsocial.com/@realDonaldTrump\nhttps://r.jina.ai/https://bitget.com/events/poolx\n```\n\n## Examples\n\n### Get Trump Truth Social posts:\n```\ncurl -s \"https://r.jina.ai/https://truthsocial.com/@realDonaldTrump\"\n```\n\n### Get any protected pag", "cost": { "context_tokens": 230 } }

Web Scraper (r.jina.ai)

About

Web Scraper using r.jina.ai

Features

Usage

Examples

Get Trump Truth Social posts:

Get any protected page:

In Code

Use Cases

Install Web Scraper (r.jina.ai) and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews