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

#342 — Top 71.4%

M-Nivetha7

Nivetha Mayilvaganan

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

The 25-Minute Developer

OrbitScope was created, coded, committed, and pushed in approximately 25 minutes. GalaxyMorphNet: 40 minutes. VR-SkinVerse-AI: 2 hours. At this pace, you could rewrite Linux by Thursday.

Untrained Model, Literally

VR-SkinVerse-AI's train_model.py contains no training loop — just model.save(). The AI is not artificial or intelligent. It's aspirational.

0 PRs, 0 Issues, 0 Following

In the past year: zero pull requests, zero issues filed, zero people followed. GitHub is a social platform. You're using it as a very public hard drive.

Tests? In This Economy?

10 out of 12 repos have no tests whatsoever. The two that do are marked HAS_TESTS=yes — but one is a Flutter app built in a single day and the other is a physiotherapy tracker created two days ago. Bold confidence.

Portfolio Breadth, Sprint Depth

Astronomy, medical AI, skin analysis, dog photography, air writing — the domains are impressive. The commit histories are not. Most repos peaked at day 1 and flatlined. Ideas are infinite; follow-through has a hard cap.

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
    56D
  • Consistency
    20% weight
    60C
  • Quality
    20% weight
    41D
  • Depth
    15% weight
    55D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    50D

03 · Stats

365-day commit heatmap

44 active days

Less
More

Language distribution

7 langs
  • Python65%
  • Jupyter Notebook30%
  • JavaScript3%
  • TypeScript1%
  • C++0%
  • CSS0%
  • Other1%

04 · Numbers

Owned repos

non-fork

30

Commits

last 12 months

348

Followers

10

Joined GitHub

Sep 2023

05 · Top repos

M-Nivetha7 /

Auto_Dog_Photographer

38/100

Personal portfolio computer vision project using YOLOv8 and OpenCV to automatically capture dog photos based on centering and stability detection. Well-documented, clean modular structure, but lacks tests/CI and has limited external adoption signals.

I25Q50D35
README
Python01mo ago

M-Nivetha7 /

Smart_Retail_Assistant

37/100

Early-stage Flutter shopping app with product search, cart, QR payment, and mock ML backend. Typed Dart code, clear structure, functional MVP but pre-production scale (305 KB, ~10 commits in 1 day, no CI/tests).

I25Q50D35
READMETests
Dart08d ago

M-Nivetha7 /

Skill-Scan

37/100

TypeScript React resume analyzer with typed components, TailwindCSS styling, and structured codebase. Lacks CI/tests but ships Docker support and meaningful project structure.

I25Q50D35
READMETyped
JavaScript11mo ago

M-Nivetha7 /

AIR-WRITING

32/100

Functional Python CV project using MediaPipe + OpenCV for gesture-based air writing. Demonstrates working hand tracking and canvas rendering across modular src/ structure, but minimal maintenance (6 of 30 commits in 1 day), no tests/CI/license, and experimental scope.

I25Q50D20
README
Python01mo ago

M-Nivetha7 /

MEDIMOTION1

25/100

Fresh AI physiotherapy tracker with pose detection via MediaPipe and TensorFlow. Bare-bones Flask backend + React frontend, minimal production readiness—no CI/tests, no license, created 2 days ago with 16 commits. Functional proof-of-concept but deeply experimental.

I15Q40D20
READMETests
Python012d ago

M-Nivetha7 /

CosmicDataLab

25/100

Student ML project classifying astronomical objects (Stars, Galaxies, Quasars) using Random Forest on SDSS data. Typed Python, structured multi-file layout, README with setup instructions, but no tests/CI and only 6 commits in ~1.5 hours. Learning-stage work.

I15Q40D20
README
Python02mo ago

M-Nivetha7 /

m-nivetha7

23/100

A personal GitHub profile README with minimal functional code—primarily a styled bio/portfolio page listing skills and social links. Contains one CI workflow (snake animation generator) and no tests or core project logic.

I15Q25D30
READMECI
Unknown07d ago

M-Nivetha7 /

Parkinson-Disease

23/100

Jupyter Notebook-based medical ML project for Parkinson's detection via handwriting analysis. Early-stage portfolio work with documented approach but minimal commit activity (7/30), no tests/CI, untyped language, and no accessibility to source files suggests incomplete repository state.

I15Q35D20
README
Jupyter Notebook02mo ago

M-Nivetha7 /

VR-SkinVerse-AI

22/100

Early-stage skin analysis app with React frontend and Flask ML backend. Minimal production readiness: no tests, CI, license, or error handling; hardcoded API endpoint; untrained model; no input validation.

I15Q35D15
README
JavaScript013d ago

M-Nivetha7 /

OrbitScope

20/100

Single-file Python visualization project using Skyfield and Plotly for 3D satellite orbit rendering. Created and pushed on same day (2026-03-09); minimal codebase with no tests, CI, license, or version control metadata.

I15Q40D5
README
Python02mo ago

M-Nivetha7 /

Space_Research_2

20/100

Early-stage ML educational project on pulsar/celestial object classification using Jupyter notebook with HTRU2 dataset. Minimal commit history (5 of last 30 in ~1.5 hours), no tests, CI, license, or gitignore.

I15Q35D10
README
Jupyter Notebook02mo ago

M-Nivetha7 /

GalaxyMorphNet

18/100

Single-notebook Jupyter ML project for galaxy morphology classification using Random Forest/SVM/KNN. Well-documented README but no tests, CI, typed code, or modular structure. Created and completed in one session with zero adoption signals.

I15Q35D5
README
Jupyter Notebook02mo ago

06 · Timeline

  1. Sep 19, 2023
    Joined GitHub
  2. Oct 25, 2025
    Created Skill-Scan — Skill Scan is an AI-powered resume checker that analyzes resumes to evaluate a candidate's skills, strengths, and gaps. It scans resume content, detects key skills, checks formatti
  3. Nov 29, 2025
    Created m-nivetha7 — A professional GitHub profile that highlights my skills, achievements, technical interests, and the creative tools I use in my AI and ML projects. It reflects my journey as an aspi
  4. Mar 8, 2026
    Created Space_Research_2 — This project uses machine learning to classify celestial objects, focusing on pulsar star identification. It contains a Jupyter notebook (pulsar.ipynb) for analysis and results bas
  5. Mar 8, 2026
    Created GalaxyMorphNet — Space_Research_3 is a machine learning project that classifies galaxies into spiral, elliptical, or irregular types using image data, applying models like Random Forest, SVM, and K
  6. Mar 9, 2026
    Created CosmicDataLab — Analyzes space-related datasets using machine learning and data analysis techniques to identify patterns and insights. The project involves data preprocessing, visualization, and m
  7. Mar 9, 2026
    Created OrbitScope — OrbitScope visualizes satellite orbits around Earth using Python. It calculates satellite positions from TLE orbital data with Skyfield and displays an interactive 3D orbit simulat
  8. Mar 16, 2026
    Created Parkinson-Disease
  9. Apr 13, 2026
    Created AIR-WRITING — A real-time computer vision project that lets users write in the air using hand gestures via a webcam. It uses MediaPipe for hand tracking and OpenCV for drawing on a virtual canva
  10. Apr 25, 2026
    Created Auto_Dog_Photographer — Auto Dog Photographer is a fun computer vision project that uses Python, OpenCV, and YOLO to automatically capture photos of a dog when it is centered and stable in front of the ca
  11. May 21, 2026
    Created VR-SkinVerse-AI
  12. May 22, 2026
    Created MEDIMOTION1 — MediMotion is an AI-powered physiotherapy platform for exercise tracking, patient monitoring, reports, and recovery insights.
  13. May 25, 2026
    Created Smart_Retail_Assistant — AI-powered smart shopping app with cart tracking, store navigation, QR payment, and ML-based product recommendations.
  14. May 27, 2026
    Most recent push to m-nivetha7

07 · Compare

github.com/
M-Nivetha7 · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total53.0
Top-end curve+3.3
Final overall56.2

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.
M-Nivetha7 · 56.2/100 — Rate My GitHub