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

#203 — Top 83.1%

alaotach

AlAoTach

C

Getting there

Overall

0.0

/ 100

01 · Roasts

113 repos, 100 stars total

You have more repositories than most engineers have written functions, yet the entire portfolio averages under 1 star each. Quantity is not a portfolio strategy.

94% solo, 5 total forks

In 4+ years on GitHub, only 5 people have forked anything you've built. EryzaLabs is a company of one with zero customers.

Tests? Briefly, in 2 repos

convince-ai and evangelion-vscode are the lone survivors in a portfolio-wide test famine. The other 111 repos are shipping vibes only.

The graveyard of one-commit wonders

mood-match, iitd-profs, and kiki-player were born and abandoned within hours. You're filing bug reports against your own attention span.

README? Not for the important ones

forus (3MB codebase, 23 commits, real Firebase app) has no README. convince-ai (~88k LOC estimate) has no README. You built the house but removed the door.

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
    57D
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    65C
  • Community
    10% weight
    25F

03 · Stats

365-day commit heatmap

202 active days

Less
More

Language distribution

7 langs
  • JavaScript55%
  • TypeScript24%
  • Python11%
  • C#2%
  • C++2%
  • ShaderLab1%
  • Other5%

04 · Numbers

Owned repos

non-fork

86

Commits

last 12 months

708

Followers

8

Joined GitHub

Mar 2021

05 · Top repos

alaotach /

propose-day

42/100

Romantic proposal website template in TypeScript/React with multi-page flow, animations (Framer Motion, GSAP), circular carousel gallery, and customizable content via config.ts—personal project with modest adoption (1 star) but complete feature set and structured codebase.

I25Q55D45
READMETyped
TypeScript12mo ago

alaotach /

convince-ai

41/100

Convince-AI is a React Native + web chat app that lets users debate whether an AI or human is authentic. Typed, multi-client, with backend API integration and persistent storage. No README, no license, no CI.

I25Q50D50
TestsTyped
TypeScript21mo ago

alaotach /

evangelion-vscode

40/100

Evangelion-themed VS Code extension with 5 color themes and sidebar panel. Typed TypeScript, structured layout, tests present, but no CI and no license. 25KB codebase with diagnostic display and theme switching functionality. Created 2 days ago with 25/30 recent commits.

I25Q60D35
READMETestsTyped
TypeScript11mo ago

alaotach /

forus

38/100

Forus: couples' relationship app (React Native + Expo + TypeScript + Firebase + Express backend) with chat, vault, daily writing, moods. Typed, structured, documented via code, no tests/CI. 3MB codebase, 23 recent commits over 10 months in new repo.

I25Q50D40
Typed
TypeScript11mo ago

alaotach /

aloo-mc-shader

37/100

Minecraft shader template with foundational Iris support (shadow mapping, lighting pipeline, 8 commits over 3 weeks). Working project structure with GLSL shaders, clear README, and build tooling. Minimal scope—starter template rather than feature-rich shader.

I25Q50D35
README
GLSL11mo ago

alaotach /

tab-sleep

32/100

Early-stage browser extension for automatic tab memory management. Functional MVP with working auto-sleep, manual controls, and whitelist features; untyped JS and no tests/CI limit polish.

I15Q45D35
README
JavaScript11mo ago

alaotach /

guess-the-error

30/100

Personal web game that integrates http.cat/http.dog APIs with AI-generated hints via Netlify functions. Functional but minimal scope, untyped JavaScript, no tests or CI. One-off indie project with limited ecosystem relevance.

I15Q40D35
README
JavaScript22mo ago

alaotach /

groupify

28/100

Early-stage Chrome extension for tab grouping with minimal adoption. Has working core features (group creation, saving, searching) but lacks tests, CI, and was only released today with 1 star. Needs maturation before production use.

I25Q40D20
README
JavaScript11mo ago

alaotach /

khana-khazana

28/100

Personal Flask recipe-sharing app with functional features (image uploads, rate limiting, recipe CRUD) but minimal documentation, no tests, and thin architectural scope. Works but early-stage.

I25Q40D20
README
HTML11mo ago

alaotach /

iitd-profs

15/100

One-shot data scraper for IIT Delhi faculty across multiple departments. Minimal scope: pre-parsed static data embedded in Python files, no live web scraping, no tests, no docs, created and pushed same day (2026-03-21, 1 commit).

I15Q25D5
Python22mo ago

alaotach /

mood-match

7/100

Empty scaffold Flask app with no documentation, tests, or meaningful functionality. Single commit on 2026-03-22 with only a placeholder home route. Not production-ready.

I5Q10D5
Python12mo ago

alaotach /

kiki-player

2/100

Empty scaffold created 2026-04-30 with zero commits, no files, no documentation, and no build artifacts. Appears to be an uninitialized repository placeholder.

I5Q0D5
Unknown01mo ago

06 · Timeline

  1. Mar 25, 2021
    Joined GitHub
  2. Jun 21, 2025
    Created convince-ai
  3. Jun 28, 2025
    Created forus
  4. Jan 7, 2026
    Created guess-the-error
  5. Feb 7, 2026
    Created tab-sleep
  6. Feb 8, 2026
    Created propose-day
  7. Mar 21, 2026
    Created iitd-profs
  8. Mar 22, 2026
    Created mood-match
  9. Apr 4, 2026
    Created evangelion-vscode
  10. Apr 6, 2026
    Created khana-khazana
  11. Apr 7, 2026
    Created aloo-mc-shader
  12. Apr 8, 2026
    Created groupify
  13. Apr 30, 2026
    Created kiki-player
  14. Apr 30, 2026
    Most recent push to kiki-player

07 · Compare

github.com/
alaotach · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total57.6
Top-end curve+4.4
Final overall62.0

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.
alaotach · 62.0/100 — Rate My GitHub