docs: improve LLM optimization guide with usage examples and cross-links

[tien9486]

What changed? Why?

• The LLM-optimized files (llms.txt, llms-full.txt, docs-llms.mdx) are great for discoverability but can be improved for better LLM consumption and developer experience. Add a clear "How to Use These Files" section, more explicit prompt examples, cross-references to prompt-library.mdx and relevant sections (e.g., Base Chain API, Agents), and a simple validation snippet.

• Aligns with AI-agents push on Base; makes docs more actionable for builders using LLMs/Cursor/Claude to generate Base code. Small, high-impact, no structure changes.

Notes to reviewers

• Focused PR touching docs/get-started/docs-llms.mdx, regenerate/update llms*.txt via scripts if applicable, minor links in related files.

• Add cross-links in prompt-library.mdx and agents.md pointing back to LLM docs.

• Ensure code blocks specify language (e.g., bash, solidity).

• Update any outdated references if found during review (e.g., network details post recent upgrades like v0.8/v0.9).

[cb-heimdall]

🟡 Heimdall Review Status

Requirement	Status	More Info
Reviews	🟡 0/2	Denominator calculation Show calculation 1 if user is bot 0 1 if user is external 0 2 if repo is sensitive 0 From .codeflow.yml 1 Additional review requirements Show calculation Max 0 0 From CODEOWNERS 0 Global minimum 0 Max 1 1 1 if commit is unverified 1 Sum 2