01 · Roasts
Sprint-and-Ghost Developer
EarthTwin, EarthVoice, EarthTwin-Backend, and EarthVoice-Backend were ALL created on 2026-04-20 and last pushed on 2026-04-20. You shipped four repos in one day and walked away. That's not a portfolio, that's a fever dream.
Zero Tests, Zero CI, Every Repo
Across all 9 analyzed repos — 0 have tests, 0 have CI. Not one. You've got GLSL shaders, Gemini integrations, and MCP orchestration, but apparently `npm test` is a foreign concept.
The Boilerplate Hall of Fame
CodeXHackthon has a README that is literally the unmodified Create React App default. 3 stars. Someone starred a README that says 'You can learn React at https://reactjs.org'. This is your highest-star repo.
Following: 0. Following Nobody.
38 followers, following literally 0 people. You're not networking, you're broadcasting into the void. No issues opened this year, 7 PRs total — the open-source 'contributor' in your bio is working overtime for that label.
The Heatmap Tells the Truth
207 commits this year sounds okay until you see the heatmap: a green burst in weeks 1–9, then 30+ consecutive weeks of near-silence. You code in seasonal migrations, not sustained engineering.
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% weight62C
- Consistency20% weight55D
- Quality20% weight57D
- Depth15% weight50D
- Breadth10% weight65C
- Community10% weight55D
03 · Stats
365-day commit heatmap
47 active days
Language distribution
- JavaScript40%
- TypeScript28%
- CSS11%
- HTML8%
- Python5%
- Java4%
- Other4%
04 · Numbers
Owned repos
non-fork
69
Commits
last 12 months
207
Followers
38
Joined GitHub
Aug 2022
05 · Top repos
TheCoderAdi /
EarthTwin
Early-stage React+TypeScript interactive 3D globe app simulating environmental impact via lifestyle choices. Typed frontend with shader-based rendering, but brand-new (2 days), no tests/CI, thin documentation, and zero adoption signal.
TheCoderAdi /
the-council
Early-stage multi-agent AI debate system using Model Context Protocol to integrate Gemini/Groq LLMs with Notion. Typed JavaScript with structured architecture, but minimal community adoption (0 stars, created 2026-03-15, 6 commits in ~2 days).
TheCoderAdi /
IdeaLens
TypeScript Next.js frontend for AI creative assistant (IdeaLens). Typed, documented with README + demo, structured src layout. New project (created Apr 2025) with 30 recent commits, but no tests, CI, or license. Minimal adoption (1 star), unproven market impact.
TheCoderAdi /
cricksquad
A newly created weekend cricket management app with RSVP, team balancing, scorecards, and Gemini AI integration. Typed JS stack (React/Node), structured layout, and README present, but ultra-recent (created 2026-03-01), minimal commit history (6 of last 30), and zero production signals.
TheCoderAdi /
EarthVoice-Backend
Minimal Node.js/Express backend for EarthVoice narrative platform. Untyped JavaScript, thin documentation, 2 commits in 45 minutes. Personal early-stage project with no external adoption signals.
TheCoderAdi /
EarthVoice
Voice-forward 3D globe UI exploring environmental themes. TypeScript + React 19 + Tailwind with interactive features (narrative, chat, memory timeline), but nascent project (2 commits in 46 minutes, 90 KB) with no tests/CI and no production adoption signals.
TheCoderAdi /
EarthTwin-Backend
Minimal Express-based API for environmental impact analysis using Gemini, with basic simulation logic. One-week sprint project (3 commits in 2 days), untyped JavaScript, no tests/CI, intentionally lightweight starter.
TheCoderAdi /
simple_react_projects
Create React App boilerplate with minimal customization; 7MB codebase, 30 commits over 3+ years, no tests/CI/license, untyped JavaScript, generic README describing CRA defaults only.
TheCoderAdi /
CodeXHackthon
Unmodified Create React App boilerplate with generic README. Minimal customization visible, 3 stars, no tests/CI/license/types. Personal hackathon entry test project with thin output.
06 · Timeline
- Aug 15, 2022Joined GitHub
- Dec 8, 2022Created simple_react_projects
- Feb 19, 2023Created CodeXHackthon — This is entrance test for the very popular club of ITER ( CodeX)
- Apr 10, 2025Created IdeaLens — LeadLens is an AI-powered creative assistant that helps you generate, refine, and analyze content ideas. This frontend is built using Next.js App Router, Tailwind CSS, shadcn/ui, a
- Mar 1, 2026Created cricksquad
- Mar 15, 2026Created the-council
- Apr 19, 2026Created EarthTwin-Backend
- Apr 20, 2026Created EarthTwin
- Apr 20, 2026Created EarthVoice-Backend
- Apr 20, 2026Created EarthVoice
- Apr 20, 2026Most recent push to EarthTwin
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.