01 · Roasts
Notebook monoculture
87% of the language mix is Jupyter Notebook; the profile says ML, but reusable package-grade Python is still scarce.
CI has not been invited
Across the showcased projects, CI is absent everywhere—even Credimerge, the one repo with tests, ships without it.
GigCred multiverse
Gig, u, -ll, test-12, and Credimerge repeatedly reinvent financial tooling; consolidate the strongest version and give it a real README.
Documentation roulette
Churnpredictai and IPL-Analysis explain themselves, while several substantial apps have no README at all and Credimerge says “huhuhrufhunf.”
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% weight65C
- Quality20% weight52D
- Depth15% weight55D
- Breadth10% weight55D
- Community10% weight25F
03 · Stats
365-day commit heatmap
104 active days
Language distribution
- Jupyter Notebook87%
- TypeScript10%
- Python3%
- HTML0%
- CSS0%
- JavaScript0%
04 · Numbers
Owned repos
non-fork
34
Commits
last 12 months
587
Followers
6
Joined GitHub
Oct 2024
05 · Top repos
Bhupendra-glitch /
IPL-Analysis
A documented Streamlit IPL analytics dashboard with substantial multi-page code, visualizations, and lightweight prediction features, but limited adoption and notable unfinished or duplicated modules.
Bhupendra-glitch /
Churnpredictai
A documented Streamlit churn dashboard with prediction, K-means segmentation, metrics, and business recommendations, but limited adoption evidence and no tests or CI.
Bhupendra-glitch /
Portfolio
A typed React/Vite portfolio with a polished single-page UI, nine skill categories, and multiple project/experience claims, but minimal documentation and no tests, CI, license, or demonstrated external adoption.
Bhupendra-glitch /
Gig
Gig is a substantial typed React/Express financial-intelligence demo with interactive cashflow scoring, loan simulation, multilingual assistance, and mock personas, but it has no documented adoption or engineering validation signals.
Bhupendra-glitch /
Credimerge
Typed React/Node financial platform with tests and a substantial 44,374 KB footprint, but currently has minimal documentation, no CI or license, and exposes a hard-coded MongoDB connection configuration.
Bhupendra-glitch /
-ll
A substantial typed TypeScript GigCred demo with React UI, Express/Gemini endpoints, Firebase persistence, multilingual counseling, and Monte Carlo lending simulation, but it has 0 stars and no tests, CI, license, or README.
Bhupendra-glitch /
test-12
A substantial TypeScript React/Express GigCred financial dashboard with EMI, stress testing, Monte Carlo, and AI-advice flows, but it is an undocumented, untested two-commit demo with no visible adoption.
Bhupendra-glitch /
u
Typed React/Express financial-debt simulator with deterministic EMI, consolidation, repayment, and AI explanation flows, but currently a 0-star one-shot repository with no tests, CI, license, or project documentation.
Bhupendra-glitch /
Kaggriculture
Kaggriculture is a thoroughly specified farming-game competition guide, but the sampled repository shows only documentation, no tests, CI, typed implementation, license, or adoption evidence.
Bhupendra-glitch /
run-
A one-kilobyte, one-commit scaffold containing only an AI Studio README banner and no fetched source files, tests, CI, license, or typed implementation.
06 · Timeline
- Oct 6, 2024Joined GitHub
- Feb 13, 2026Created Churnpredictai — Built a machine learning classification model to predict customer churn using telecom customer data.
- Feb 13, 2026Created IPL-Analysis — This project performs Exploratory Data Analysis (EDA) on IPL match-level and ball-by-ball datasets to uncover team and player performance insights across 15+ seasons
- Mar 28, 2026Created Portfolio — Just
- Aug 7, 2026Created Kaggriculture — Kaggle x Google
- Sep 18, 2026Created -ll — Test
- Sep 20, 2026Created u — 7
- Sep 20, 2026Created Gig — GFG
- Sep 21, 2026Created run- — run
- Sep 21, 2026Created test-12 — effef
- Sep 21, 2026Created Credimerge — GigCred is an AI-powered financial intelligence and credit-health platform designed for gig workers, freelancers, micro-merchants, and new-to-credit users. It analyzes income, expe
- Sep 22, 2026Most recent push to Credimerge
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.