⚡ Bolt: optimize README assets and payload

[soktri3]

This PR implements several performance optimizations for the organization's profile README and its assets:

1. SVG Asset Optimization: Both logo.svg and logo-dark.svg were minified using svgo with --multipass --precision 1 and manual comment removal. This ensures the smallest possible asset weight for initial profile loads.
2. LCP Performance: Added fetchpriority="high" and decoding="async" to the primary logo <img> tag. This hints the browser to prioritize the brand asset and avoids blocking the main thread during decoding, improving the Largest Contentful Paint (LCP) metric.
3. HTML Payload Reduction: Converted absolute GitHub URLs (e.g., https://github.com/modelcontextprotocol/...) to root-relative paths (/modelcontextprotocol/...). This reduces the number of bytes in the README file and leverages GitHub's internal routing for faster navigation.

Visual integrity was verified using Playwright screenshots to ensure the logos render correctly in both light and dark modes after optimization.

---

PR created automatically by Jules for task 7081564540430971860 started by @soktri3

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[gemini-code-assist]

Code Review

This pull request optimizes the organization's profile README by converting internal GitHub links to root-relative paths and adding performance hints to the primary brand asset. It also removes redundant comments from SVG assets. Feedback was provided regarding the use of 'decoding="async"' on the main logo; while intended for optimization, it can actually delay the Largest Contentful Paint (LCP) for critical above-the-fold assets. It is recommended to remove this attribute from the logo and update the corresponding learning notes in the documentation to reflect that 'decoding="async"' is best reserved for non-critical images.

[gemini-code-assist]

While fetchpriority="high" is a beneficial hint for the primary brand asset to improve Largest Contentful Paint (LCP), using decoding="async" on the same element can be counter-productive.

decoding="async" allows the browser to defer the decoding (or rasterization for SVGs) of the image to avoid blocking the main thread. However, for an above-the-fold image that is likely the LCP element, this can delay the actual paint of the image, potentially increasing the LCP metric. For critical, visible assets, the default decoding="auto" (or explicit sync) is generally preferred to ensure the image is rendered as soon as it is decoded.

Note: While GitHub's markdown sanitizer may currently strip these attributes, it is best practice to use them correctly for environments where they are supported.

Suggested change

	<img src="assets/logo.svg" alt="Model Context Protocol Logo" width="600" height="87" fetchpriority="high" decoding="async">
	<img src="assets/logo.svg" alt="Model Context Protocol Logo" width="600" height="87" fetchpriority="high">

[gemini-code-assist]

The learning note regarding decoding="async" is slightly inaccurate for LCP optimization. While decoding="async" improves main-thread responsiveness by offloading decoding work, it can actually delay the paint of the image, which may negatively impact the Largest Contentful Paint (LCP) metric if applied to the primary brand asset. It is best reserved for non-critical or below-the-fold images.

Suggested change

	**Learning:** Using root-relative paths for internal GitHub links reduces HTML payload and enables faster internal navigation. Adding 'fetchpriority="high"' and 'decoding="async"' to above-the-fold brand assets helps improve Largest Contentful Paint (LCP) and main-thread responsiveness.
	**Learning:** Using root-relative paths for internal GitHub links reduces HTML payload and enables faster internal navigation. Adding 'fetchpriority="high"' to above-the-fold brand assets helps improve Largest Contentful Paint (LCP), while 'decoding="async"' is better suited for non-critical assets to maintain main-thread responsiveness.