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
- Impact25% weight56D
- Consistency20% weight60C
- Quality20% weight41D
- Depth15% weight55D
- Breadth10% weight55D
- Community10% weight50D
03 · Stats
365-day commit heatmap
44 active days
Language distribution
- 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
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.
M-Nivetha7 /
Smart_Retail_Assistant
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).
M-Nivetha7 /
Skill-Scan
TypeScript React resume analyzer with typed components, TailwindCSS styling, and structured codebase. Lacks CI/tests but ships Docker support and meaningful project structure.
M-Nivetha7 /
AIR-WRITING
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.
M-Nivetha7 /
MEDIMOTION1
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.
M-Nivetha7 /
CosmicDataLab
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.
M-Nivetha7 /
m-nivetha7
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.
M-Nivetha7 /
Parkinson-Disease
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.
M-Nivetha7 /
VR-SkinVerse-AI
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.
M-Nivetha7 /
OrbitScope
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.
M-Nivetha7 /
Space_Research_2
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.
M-Nivetha7 /
GalaxyMorphNet
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.
06 · Timeline
- Sep 19, 2023Joined GitHub
- Oct 25, 2025Created 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
- Nov 29, 2025Created 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
- Mar 8, 2026Created 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
- Mar 8, 2026Created 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
- Mar 9, 2026Created 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
- Mar 9, 2026Created 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
- Mar 16, 2026Created Parkinson-Disease
- Apr 13, 2026Created 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
- Apr 25, 2026Created 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
- May 21, 2026Created VR-SkinVerse-AI
- May 22, 2026Created MEDIMOTION1 — MediMotion is an AI-powered physiotherapy platform for exercise tracking, patient monitoring, reports, and recovery insights.
- May 25, 2026Created Smart_Retail_Assistant — AI-powered smart shopping app with cart tracking, store navigation, QR payment, and ML-based product recommendations.
- May 27, 2026Most recent push to m-nivetha7
07 · Compare
08 · Rubric
How this score was produced
Overall = Σ (category × weight) + gentle top-end curve
Tier thresholds
▸ How the pipeline works
- 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.
- 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
- 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.
- 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.
- 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.