This stack is for preparing a GitHub Pages site, public project page, landing page, or portfolio surface with correct HTML structure, metadata, and machine-readable discovery files before any push. It closes publication risks at the page level — audience, role, metadata, accessibility, links, and discovery — and optionally adds a structured implementation brief and the correct set of discovery files for the deployment target. Use it whenever the page is meant to be found, indexed, or shared publicly.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/xxyoudeadpunkxx/ai-protocol-kit/llms.txt
Use this file to discover all available pages before exploring further.
Public Page Publication Protocol v2
Classify the page role and project, audit the source surface, run a publication risk audit, and design the page model before any file is generated. This protocol controls the session: it forces the right decisions about audience, page purpose, metadata, canonical URLs, and publication risks before any implementation or deployment step begins.View protocol →
HTML Page & Tool Briefing Protocol v2 (conditional)
Add this step only if an AI will build the page — that is, if implementation briefing is actually needed. This protocol guides the AI from raw intake to a complete, execution-ready brief for a static HTML page or web surface. Skip it if the page already exists or if you are not using AI to build the implementation.View protocol →
Discovery Set Protocol (conditional — choose one)
Add the appropriate discovery protocol before publishing, based on your deployment target:
- GitHub Pages deployments: GitHub Pages Discovery Set Protocol v1 — handles GitHub Pages publication roots, discovery files, canonical URLs, sitemap, robots handling, and footer links without breaking GitHub Pages path rules.
- Generic static sites: HTML and Website Discovery Set Protocol v1.2 — prepares static HTML pages or websites with machine-readable discovery files, head metadata, canonical URLs, sitemap, robots rules, and low-noise footer links.
Steps 2 and 3 are both conditional. Step 2 is only needed if an AI is building the page from scratch. Step 3 is only needed before publishing — choose the discovery protocol that matches your deployment target (GitHub Pages or generic static site), not both. Step 1 is the only default.
When to use this stack
- Building a new GitHub Pages site, project landing page, or portfolio surface with AI assistance
- Publishing an existing page that lacks correct metadata, canonical URLs, or discovery files
- Preparing any public HTML surface where discoverability and publication hygiene matter before the first push
- Structuring a page that will be linked from a repository README or shared externally