Chore: add SKILL.md retrieval policy for AI agents

[scode2277]

Adds a SKILL.md at the repository root that defines how AI agents should retrieve and answer from Frameworks content. Cross-links the new file from AGENTS.md and docs/pages/intro/llms.mdx.

Frameworks PR Checklist

Thank you for contributing to the Security Frameworks! Before you open a PR, make sure to read information for contributors and take a look at the following checklist:

• Describe your changes, substitute this text with the information
• If you are touching an existing piece of content, tag current contributors from the attribution list
• If there is a steward for that framework, ask the steward to review it
• If you're modifying the general outline, make sure to update it in the vocs.config.ts adding the dev: true parameter
• If you need feedback for your content from the wider community, share the PR in our Discord
• Review changes to ensure there are no typos; see instructions below.

[cloudflare-workers-and-pages]

Deploying frameworks with    Cloudflare Pages

Latest commit:	1cb08ce
Status:	✅  Deploy successful!
Preview URL:	https://68822772.frameworks-573.pages.dev
Branch Preview URL:	https://chore-skill-file.frameworks-573.pages.dev

View logs

[frameworks-volunteer]

Model: z-ai/glm-5.1 Reasoning: medium Provider: openrouter

Review: SKILL.md retrieval policy

Security: No issues. No secrets, no injection vectors, no unsafe eval, no new dependencies. All URLs point to known canonical domains (securityalliance.org, securityalliance.dev, github.com).

QA: Changes match the PR description — new SKILL.md, cross-links from AGENTS.md and llms.mdx, reference added in generate-llms.js. AGENTS.md HTML entity cleanup (< → <, > → >, && → &&) is a bonus fix and correct. Links are valid. No leftover debug content.

One minor nit: SKILL.md is missing a trailing newline. POSIX text files should end with \n. Worth fixing but not blocking.

Approved.