▸ This tool was built by an AI agent from Zoral
← RATE MY GITHUB

#84 — Top 93.0%

Yhozen

Gabriel Pérez

C

Getting there

Overall

0.0

/ 100

01 · Roasts

CI? Never Heard of Her

8 repos scored, only booking-system has CI=yes. You clearly know how to write tests (vitest appears in 5 repos) but you keep stopping just before automating them. The pipe dream of green checks remains a dream.

107 Repos, 24 Stars

A decade on GitHub, 107 public repos, and a grand total of 24 stars across all of them. That's a star every 5 months. At this rate you'll hit 3 digits by 2060.

The Bootstrap Phase Specialist

self-evolve's README literally admits it's in 'bootstrap phase' and the GOAL.md 'expected to live at root' doesn't exist yet. Shipped: the scaffolding for the system that will eventually decide what to build.

License? That's a Future Gabriel Problem

Multiple repos — including self-evolve and garox.org — ship with no LICENSE file. You've architected Effect service layers with typed error boundaries but forgot the one-line MIT license. Legal ambiguity as a feature.

71% Graveyard Ratio

staleRepoRatio = 0.71 means roughly 3 in 4 of your repos haven't seen a push in over 2 years. That's not a portfolio, that's a GitHub museum with a very active gift shop.

Built using

Zoral

Shadows one worker for a week, then takes over their job with zero extra setup. Behaves exactly like the original.

zoral.ai

02 · Category breakdown

  • Impact
    25% weight
    62C
  • Consistency
    20% weight
    65C
  • Quality
    20% weight
    72B
  • Depth
    15% weight
    65C
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    55D

03 · Stats

365-day commit heatmap

272 active days

Less
More

Language distribution

7 langs
  • TypeScript75%
  • MDX6%
  • JavaScript5%
  • Python5%
  • CSS5%
  • HTML1%
  • Other3%

04 · Numbers

Owned repos

non-fork

62

Commits

last 12 months

276

Followers

60

Joined GitHub

Mar 2014

05 · Top repos

Yhozen /

world-food-passport

57/100

Next.js restaurant tracker with gamified challenges system, featuring TypeScript backend, comprehensive test coverage (vitest), and detailed architecture documentation. Demonstrates solid full-stack patterns with auth, database schema, and achievement unlock mechanics.

I40Q72D58
READMETestsTyped
TypeScript02mo ago

Yhozen /

booking-system

50/100

Full-stack Next.js booking system with PostgreSQL, tRPC, Prisma ORM. TypeScript typed, comprehensive Vitest suite with PGlite local testing, clean service/DB layer separation, advanced SQL constraints using range types and exclusion constraints.

I25Q75D50
READMETestsCITyped
TypeScript02mo ago

Yhozen /

self-evolve

48/100

Bootstrap-stage TypeScript framework for autonomous self-evolving systems around goals, with sandbox orchestration abstraction, Effect-based error handling, and comprehensive documentation plan. Core infrastructure is well-architected but goal/product definition and autonomous capabilities remain incomplete.

I25Q65D50
READMETestsTyped
TypeScript01mo ago

Yhozen /

garox.org

48/100

Retro-styled Next.js personal portfolio with TypeScript, Framer Motion drag-and-drop windows UI, and state management. 2070 KB codebase with structured components and minimal documentation.

I25Q55D65
READMETyped
TypeScript04mo ago

Yhozen /

pythonCourse

38/100

Interactive Python course platform built with Create React App. 10MB codebase with recent activity, but lacks tests, CI, type safety, and meaningful project documentation beyond boilerplate CRA template.

I25Q35D55
README
JavaScript04mo ago

Yhozen /

chat

32/100

Early-stage T3 Stack chat app with tRPC subscriptions and PostgreSQL real-time notifications. Typed, tested, and documented but minimal adoption and very recent creation (1 day old).

I15Q55D25
READMETestsTyped
TypeScript13mo ago

Yhozen /

muralpay

30/100

NestJS/Prisma marketplace backend coding challenge with checkout, merchant, and payment flows; deployed to Vercel but created within 48hrs with minimal commits, no CI, and intentionally incomplete payout/stock features per README scope.

I15Q60D20
READMETestsTyped
TypeScript02mo ago

Yhozen /

bot

28/100

Experimental Next.js chatbot integrating Slack/Telegram with OpenAI via durable workflows. Typed and structured but early-stage, no tests/CI, minimal documentation beyond boilerplate README, and appears brand new (created March 12, 2026).

I15Q45D20
READMETyped
TypeScript02mo ago

06 · Timeline

  1. Mar 10, 2014
    Joined GitHub
  2. Dec 23, 2015
    Created garox.org — Personal page
  3. Mar 22, 2019
    Created pythonCourse — Interactive python lessons for an UAI's course
  4. Jan 26, 2026
    Created world-food-passport — World Food Passport is the restaurant tracker for your food world
  5. Mar 5, 2026
    Created chat
  6. Mar 11, 2026
    Created booking-system
  7. Mar 12, 2026
    Created bot
  8. Mar 27, 2026
    Created muralpay
  9. Apr 15, 2026
    Created self-evolve — A project that builds itself
  10. Apr 17, 2026
    Most recent push to self-evolve

07 · Compare

github.com/
Yhozen · 6dmedian coder

08 · Rubric

How this score was produced

Overall = Σ (category × weight) + gentle top-end curve

CategoryWeightScoreContrib.
Raw total63.6
Top-end curve+5.6
Final overall69.2

Tier thresholds

S90100Mass-producing humansA8089Ship machineB7079Solid engineerC6069Getting thereD4059README enthusiastF039GitHub tourist
▸ How the pipeline works
  1. 01Scrape.Pull every non-fork repo pushed in the last 90 days, plus your contribution calendar, followers, and language byte counts — straight from GitHub's REST & GraphQL APIs.
  2. 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
  3. 03Grade each repo. All repos run in parallel through a fast scoring model that reads the picked files and rates each one independently on Impact, Quality, and Depth — with evidence citations.
  4. 04Aggregate. A larger reasoning model combines the per-repo scores with server-computed stats (heatmap, commit cadence, language entropy, follower count) to produce the 6-dimension profile score + roasts.
  5. 05Correct.Deterministic server-side checks enforce anchor-scale floors (e.g. a profile with 2,000+ public commits can't score 30 Consistency) and recompute the final verdict.

~90 seconds per profile, ~$0.25 in compute. Total of ~240 files read across your top-12 repos. One rating per GitHub account per day.

▸ Data sources & caveats
  • Heatmap & commit totals: GitHub GraphQL contributionsCollection — covers the last 365 days, includes private repos when the user has opted in (default).
  • Language %: byte totals across the top 30 owned non-fork repos.
  • Curve: a small upward nudge centered on raw score ≈ 70, capping at 100. Prevents specialists from being unfairly penalised for narrow breadth.
  • Anchor corrections: when server-measured signals (e.g. privateWorkLikely, multiRepoVolume, follower count) mandate a minimum category score, the aggregation step enforces it. These are signal-conditional, not identity-based floors.
Yhozen · 69.2/100 — Rate My GitHub