site-extract
Site Extract
Use this when a user gives a site URL and wants a landing page built without a bloated intake process.
This stage does not synthesize. It extracts.
If you cannot trace a claim, proof point, or trust cue back to the source, label it missing or inferred. Do not quietly upgrade it into fact.
Required inputs
- primary URL
- optional product URL
- optional
--deep - optional manual brief snippets if source access is incomplete
Operator goal
Build a source record that downstream skills can trust.
More from themattberman/landing-page-factory
page-qa
Final landing-page QA pass against strategy, proof provenance, mechanism clarity, trust preservation, accessibility, and anti-slop. Gates whether a page is shippable or draft-only.
2page-strategy
Normalize raw extract or manual brief into a page strategy artifact: mechanism, offer, audience, proof provenance, CTA, preservation plan, and review flags. Mandatory before copy or build.
2page-visuals
Plan and generate visuals by preservation class: exact product, branded environment, or concept support. Uses strategy-driven shot selection and visual QA instead of generic vibe prompting.
2page-copy
Write mechanism-preserving, proof-disciplined landing page copy from strategy, brand profile, and extract language bank. Includes mandatory sharpness audit and claim control.
2brand-profile
Build an evidence-backed brand profile from site extract and page strategy. Separates observed facts from synthesis so downstream skills preserve the brand instead of rewriting it.
2page-build
Build a deployable landing page from strategy, copy, visuals, and brand profile using category-aware routing, preservation hierarchy, and explicit QA. Single-file HTML output.
2