Gallery — real scores, no login

Three use cases. One scoring engine.

Every card below is a live score sitting in the database — click any one to see the per-metric breakdown, judge rationale, and ranked suggestions. To score your own URL, ticket, or PR, you'll need an account.

Gallery scores are being generated. Cards will fill in within a few minutes — refresh to see them appear.

Use case · Landing pages

Score any webpage through a customer lens.

Same judge, four real homepages. The rationale cites copy from each page — these are real scores, not screenshots.

customer-centric

Judge homepage (this site)

—/ 100

Pending — this score is being generated.

customer-centric

Stripe

—/ 100

Pending — this score is being generated.

customer-centric

Linear

—/ 100

Pending — this score is being generated.

customer-centric

Vercel

—/ 100

Pending — this score is being generated.

Use case · Engineering tickets

Score any text artifact — even a Linear ticket.

The spec-completeness rubric scores a vague 'Fix slow dashboard' ticket against scope, acceptance criteria, success metric, and edge cases. Same engine works for any text artifact.

spec-completeness

ENG-1234 · "Fix slow dashboard"

—/ 100

Pending — this score is being generated.

Use case · Code PRs via MCP

Score a real GitHub PR — diff, description, and all.

A merged Vercel/SWR PR fetched live via the GitHub API and judged by code-quality. Connect the GitHub App and this happens automatically on every PR.

code-quality

vercel/swr · PR #4243

—/ 100

Pending — this score is being generated.

Score your own — 30 seconds, no card.

Sign up to score your homepage, your latest PR, or any text artifact your team ships. The system rubrics are seeded; you can mint a custom one from a one-line prompt.