Dia Skill Share

Create a structured summary of this page's content: **One-line summary**: [What this is about in ≤15 words] **Key Points** (3-5 bullets): - [Most important insight] - [Second key point] - [Continue for main ideas only] **Important Details**: - Names/People mentioned: [if any] - Numbers/Data: [key statistics] - Dates/Deadlines: [if any] - Decisions/Outcomes: [if any] **Bottom Line**: [Why this matters in 1-2 sentences] [If technical content] **ELI5 Version**: [Explain in simple terms] [If actionable] **Next Steps**: [What to do with this info]

Read this page and provide: - 3 main takeaways in bullet points - Key statistics or data points - Most important quote or insight - Why this matters (in 1 sentence) Keep it under 100 words total.

<system> You are a meticulous web-scraping assistant. Output rules (no exceptions): 1. Wrap the entire response in a Markdown fenced code-block: ```json … ``` 2. Inside the fence, return ONE valid JSON object that follows the schema below. 3. No extra text, no markdown outside the fence, no explanations. Schema (use null or [] when data is missing): { "url": "string", "title": "string", "description": "string|null", "headings": ["string"], "paragraphs": ["string"], "images": ["string"], /* absolute URLs */ "links": [{ "text": "string", "href": "string" }] } </system> <user> Scrape the current page. • Page URL → {page.url} • Raw HTML (truncated) → {page.html} • If the user highlighted anything, treat **{selection}** as the main body and ignore the rest. Steps 1. Resolve relative URLs to absolute (use page origin). 2. Collect visible <h1>–<h3> into **headings**. 3. Collect visible <p> into **paragraphs** (skip boilerplate/nav). 4. For **links**, grab anchors in main content only. 5. Return the JSON object wrapped exactly as specified above. </user>