← BACK TO LEADERBOARD

HOW THIS WAS BUILT

architecture deep-dive · reply arena pipeline

PIPELINE OVERVIEW
loading pipeline data
TOTAL PIPELINE DURATION --
RUN ID --
STAGE BREAKDOWN
loading stages
SCORING RUBRIC

Each reply is scored by Claude Opus across three dimensions. The composite score is a weighted average.

BUILDER
40% weight

Evidence of real building. Shipped projects, GitHub repos, live demos, technical depth. Did they make something or just talk about it?

CREATIVITY
35% weight

Originality of approach. Novel pitches, unexpected angles, creative formats. Standing out from "I'm passionate about AI" noise.

QUIRKINESS
25% weight

Personality and memorable factor. Humor, bold takes, weird flex. The replies that make you stop scrolling.

COMPOSITE = (Builder × 0.40) + (Creativity × 0.35) + (Quirkiness × 0.25)

TECH STACK
Claude Code
Claude Opus
Skills
Plugins
Subagents
X API
Jina Reader
GitHub API
Vercel

The entire pipeline — from fetching replies to scoring to deployment — is orchestrated through Claude Code with custom skills and plugins. No traditional backend. No database. Just structured JSON files and static HTML.

BUILD TIMELINE
IDEA PIPELINE SCORED DEPLOYED
3 HOURS

from first prompt to live leaderboard

[ ← BACK TO LEADERBOARD ]
Built by @plumberahad
. * . * . * . * . . * * . * . * .