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

#57 — Top 95.3%

chintakjoshi

Chintak Joshi

B

Solid engineer

Overall

0.0

/ 100

01 · Roasts

280 PRs, 0 Audience

You opened 280 PRs this year and have exactly 0 followers to show for it. Every single one was a conversation with yourself—impressive solo theatre, but GitHub is a team sport.

The Heatmap Cliffhanger

Weeks 1–35 of your heatmap are a barren tundra of zeros. Then weeks 41–52 go full scorched-earth. Your commit history reads like someone just discovered deadlines exist.

Tests Are Also a Product

authSDK has SAML, TOTP, brute-force protection, and webhook retries—but WhatIsAroundMe, Custom-RAG-Pipeline, orbital-sweep, and the template repo collectively have zero tests. You'll architect a signing-key rotation before writing a single assert.

91 MB of Vibes

orbital-sweep is a 91 MB Three.js game with 2 years of commits, 0 stars, no license, no CI, and no types. That's a lot of polygon math for a repo that technically doesn't legally exist yet.

Portfolio Inception

You built a portfolio site (chintakjoshi) to show off your projects, then built go-llm-chatbot specifically to power it, then built authSDK to auth into it. At some point the scaffolding became the skyscraper.

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
    68C
  • Consistency
    20% weight
    65C
  • Quality
    20% weight
    72B
  • Depth
    15% weight
    65C
  • Breadth
    10% weight
    80A
  • Community
    10% weight
    40D

03 · Stats

365-day commit heatmap

124 active days

Less
More

Language distribution

7 langs
  • Python28%
  • JavaScript22%
  • CSS18%
  • TypeScript14%
  • SCSS8%
  • HTML5%
  • Other5%

04 · Numbers

Owned repos

non-fork

32

Commits

last 12 months

650

Followers

0

Joined GitHub

Sep 2022

05 · Top repos

chintakjoshi /

TWA-OSS

60/100

Multi-portal workforce platform (FastAPI + React) for justice-involved jobseeker matching with employers. Fully typed, documented, tested, and CI/CD ready with comprehensive architecture across backend (SQLAlchemy, Alembic), three frontend portals, and shared auth library.

I40Q75D65
READMETestsCITyped
TypeScript01mo ago

chintakjoshi /

go-llm-chatbot

57/100

Production-ready Go/Gin chatbot backend with dual LLM providers, JWT auth, guardrails, and structured logging. Well-architected personal portfolio project with tests and comprehensive documentation.

I40Q72D58
READMETestsTyped
Go01mo ago

chintakjoshi /

authSDK

55/100

Multi-service auth platform with FastAPI service, reusable Python SDK, comprehensive docs, tested CI/CD, and typed code. Active development with 0 stars but well-engineered production-ready foundation.

I40Q75D50
READMETestsCI
Python018d ago

chintakjoshi /

Custom-RAG-Pipeline-with-Neural-Retrieval

50/100

A complete neural RAG pipeline with BM25, bi-encoder, cross-encoder, ColBERT, distillation, and Ollama generation. Typed Python, well-structured multi-stage architecture, comprehensive docs in README, FastAPI serving, and MLflow tracking. No tests or CI evident, created 17 days ago with 17 commits.

I40Q60D50
README
Python02mo ago

chintakjoshi /

fullstack-app-template-for-authSDK-service

45/100

Well-documented full-stack template (React+FastAPI+authSDK) demonstrating browser-session auth flows. Typed TypeScript and Python, structured multi-service layout (frontend/, protected-api/), Docker Compose setup, but no tests, CI, or production adoption signals.

I25Q60D50
READMETyped
TypeScript01mo ago

chintakjoshi /

manuscriptly

45/100

Fictional agentic writing workspace prototype (Flask + React) with agent tool-calling loop, SSE streaming, and content generation. Typed backend, documented, CI tested, but zero adoption signal and explicitly prototype/fictional.

I25Q60D50
READMECI
Python02mo ago

chintakjoshi /

WhatIsAroundMe

45/100

Personal location-discovery app (React Native + Node.js) with integrated Google Places API. TypeScript typed, well-documented README, proper folder structure, but no tests/CI and 0 stars—early-stage portfolio project.

I25Q60D50
READMETyped
TypeScript02mo ago

chintakjoshi /

sync-playlist

45/100

Personal hobby project integrating Spotify and YouTube Music playlists via Go backend + Next.js frontend with OAuth, token encryption, and rate limiting. 2 stars, low adoption, but represents substantial non-trivial work.

I25Q60D50
READMETestsTyped
Go22mo ago

chintakjoshi /

chintakjoshi

38/100

Personal portfolio/about-me web app in TypeScript with 103KB codebase, CI present but no tests, minimal README, no external adoption signals or named product positioning.

I25Q40D50
READMECITyped
TypeScript01mo ago

chintakjoshi /

orbital-sweep

38/100

Learning-focused 3D game built with Three.js and gl-matrix. Demonstrates sustained development (27/30 recent commits, April 2024–March 2026) and architectural scope (91 MB codebase) but lacks tests, CI, type safety, and advanced documentation.

I25Q40D50
README
JavaScript02mo ago

06 · Timeline

  1. Sep 7, 2022
    Joined GitHub
  2. May 4, 2023
    Created chintakjoshi — This is a (GET TO KNOW ME) web app.
  3. May 25, 2023
    Created TWA-OSS — The TWA is an initiative at Saint Louis University aimed at supporting individuals at risk of incarceration to lead productive lives without returning to prison. TWA specifically f
  4. Apr 23, 2024
    Created orbital-sweep — A browser and mobile friendly 3D game where you collect orbital debris in space, built to learn Three.js and gl-matrix.
  5. Oct 9, 2025
    Created go-llm-chatbot — A secure, prod-ready service built with Go and Gin that powers an AI-driven personal portfolio chatbot. The service enables conversational interactions about my skills, projects
  6. Nov 4, 2025
    Created sync-playlist — Playlist Tracker allows users to transfer and sync playlists across multiple music platforms including YouTube Music, Spotify, Apple Music, and Amazon Music.
  7. Nov 20, 2025
    Created WhatIsAroundMe — A location-based discovery app that helps users find interesting places near their current location. The app display's nearby points of interest on an interactive map and in a sear
  8. Feb 9, 2026
    Created manuscriptly — This is a fictional prototype of a content writing agent
  9. Feb 20, 2026
    Created authSDK — This AuthSDK functions as a SDK that supports integration with multiple services.
  10. Mar 18, 2026
    Created Custom-RAG-Pipeline-with-Neural-Retrieval — A RAG system that replaces standard BM25/FAISS retrieval with a fully learned neural retrieval stack - including a fine-tuned bi-encoder, a cross-encoder reranker, ColBERT-style la
  11. Mar 20, 2026
    Created fullstack-app-template-for-authSDK-service — This is a template repository for testing authSDK service. Please find the link attached for the authSDK repo.
  12. May 16, 2026
    Most recent push to authSDK

07 · Compare

github.com/
chintakjoshi · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total66.2
Top-end curve+5.8
Final overall72.0

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.
chintakjoshi · 72.0/100 — Rate My GitHub