opengraph-io
Extract web data, capture screenshots, scrape content, and generate AI images via OpenGraph.io. Use when working with URLs (unfurling, previews, metadata), capturing webpage screenshots, scraping HTML content, asking questions about webpages, or generating images (diagrams, icons, social cards, QR codes). Triggers: 'get the OG tags', 'screenshot this page', 'scrape this URL', 'generate a diagram', 'create a social card', 'what does this page say about'.
Why use this skill?
Enhance your AI agent with OpenGraph.io. Effortlessly scrape website content, capture high-quality screenshots, and generate custom visuals and diagrams.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/primeobsession/opengraph-io-skillWhat This Skill Does
The opengraph-io skill is a versatile OpenClaw integration that acts as a bridge between your AI agent and the live web. It provides a robust suite of tools for URL unfurling, high-fidelity screenshot capturing, advanced webpage scraping, and AI-powered content querying. Beyond simple data extraction, the skill empowers agents to generate high-quality visual assets—including technical diagrams, QR codes, icons, and sophisticated marketing illustrations—directly via an intuitive API.
Installation
Installation is streamlined via the ClawHub CLI. Execute the command clawhub install openclaw/skills/skills/primeobsession/opengraph-io-skill. After installation, you must authenticate the skill. You can either place your apiKey directly into your ~/.clawdbot/clawdbot.json configuration file under the opengraph-io entry, or export your key as the OPENGRAPH_APP_ID environment variable. Ensure you have an account at dashboard.opengraph.io to retrieve your API key.
Use Cases
This skill is perfect for research assistants, automated marketing agents, and developers. Use it to generate link previews for Slack or discord reports, scrape unstructured data from legacy websites into a structured JSON format, or document system architectures through auto-generated diagrams. It is also an excellent tool for marketing teams needing to dynamically generate social media assets, such as promotional cards with embedded QR codes, based on current webpage content.
Example Prompts
- "Can you please scrape the content from https://example.com/blog and summarize the main arguments made by the author?"
- "I need a technical diagram showing the data flow between a client, our load balancer, and the database. Use Mermaid syntax for the diagram."
- "Take a full-page screenshot of https://github.com/openclaw/core and save the metadata for my records."
Tips & Limitations
To optimize performance, utilize specific endpoints rather than generic scrapes whenever possible; for instance, use the extract endpoint with defined CSS selectors to avoid parsing unnecessary HTML overhead. When generating diagrams, prioritize providing direct code to ensure high layout reliability, as AI-generated layouts can vary. Note that the free tier is limited to 100 requests per month for extraction and 4 for image generation, so ensure your agents are optimized for caching or periodic rather than continuous polling. Finally, if you encounter geo-blocking during a scrape, ensure the use_proxy flag is enabled in your configuration to route requests appropriately.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-primeobsession-opengraph-io-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api