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

#628 — Top 63.8%

nikhil00shinde

Nikhil Shinde

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

Portfolio, not pull requests

108 public repositories produced 1 total star and 0 forks: lots of shelves, little evidence anyone is borrowing the books.

Automation allergy

Most highlighted projects omit CI and licenses; even the well-structured Distributed-Task-Queue stops before automation.

Notebook monoculture

97% of language bytes are Jupyter Notebook, while the portfolio claims systems breadth through much smaller Java, Python, and shell work.

Scaffold collector

MusicBook and Build-a-Custom-Agent-Harness-from-scratch are essentially empty, and url-shortner-typescript is 0 KB.

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
    48D
  • Consistency
    20% weight
    55D
  • Quality
    20% weight
    57D
  • Depth
    15% weight
    50D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    40D

03 · Stats

365-day commit heatmap

151 active days

Less
More

Language distribution

6 langs
  • Jupyter Notebook97%
  • Java1%
  • Shell1%
  • Python1%
  • JavaScript0%
  • TypeScript0%

04 · Numbers

Owned repos

non-fork

89

Commits

last 12 months

265

Followers

15

Joined GitHub

Apr 2021

05 · Top repos

nikhil00shinde /

Distributed-Task-Queue

38/100

A documented Java 21 multi-module Spring Boot task-queue scaffold with solid domain validation and API tests, but Redis/worker modules remain planned and adoption is absent.

I20Q60D35
READMETyped
Java016d ago

nikhil00shinde /

neetcode-submissions

32/100

A documented NeetCode submission archive with Java and Python solutions spanning algorithm topics, but no tests, CI, license, or evidence of external adoption.

I20Q40D35
READMETyped
Java016d ago

nikhil00shinde /

dotfiles

30/100

A documented personal Fedora/Bluefin dotfiles repo with GNU Stow packaging and a substantial Neovim setup, but no adoption signals, tests, CI, license, or gitignore and only modest repository scope.

I20Q35D35
README
Lua01mo ago

nikhil00shinde /

Incident-triage-agent

25/100

Small Python/OpenAI incident-triage prototype with Pydantic response models, CLI analysis, evaluation cases, and streaming demo, but minimal documentation and no tests, CI, license, or demonstrated adoption.

I20Q35D20
README
Python01mo ago

nikhil00shinde /

AI-Interview-Coach

25/100

A documented, small Python CLI that uses OpenAI streaming and Pydantic validation to generate five-question mock interviews, but it has no tests, CI, license, or demonstrated adoption.

I20Q40D10
README
Python02mo ago

nikhil00shinde /

nikhil00shinde

20/100

A documented GitHub profile configuration repository with 1 star and no sampled source files; it presents a professional skills and contact README but offers little evidence of a substantive software product.

I15Q25D20
README
Unknown123d ago

nikhil00shinde /

lld

18/100

A small Java LLD practice repository with several design exercises, but no adoption signals, documentation, tests, CI, or license; sampled implementations contain multiple compile-time and logic errors.

I15Q20D20
Typed
Java02mo ago

nikhil00shinde /

MusicBook

5/100

MusicBook is an effectively empty 1 KB repository with a single commit and no fetched source files, documentation, tests, CI, or product evidence beyond its description.

I5Q10D5
Unknown016d ago

nikhil00shinde /

Build-a-Custom-Agent-Harness-from-scratch

5/100

Empty repository scaffold with only a minimal README, no source files, tests, CI, license, or gitignore, and one sampled recent commit.

I5Q10D5
README
Unknown02mo ago

nikhil00shinde /

url-shortner-typescript

3/100

Empty repository with no source files, documentation, tests, CI, license, or recorded commits.

I5Q0D5
Unknown03mo ago

06 · Timeline

  1. Apr 22, 2021
    Joined GitHub
  2. May 4, 2021
    Created nikhil00shinde — Config files for my GitHub profile.
  3. May 23, 2025
    Created dotfiles — My simple dotfiles
  4. Dec 26, 2025
    Created lld — lld problems java
  5. Apr 7, 2026
    Created Distributed-Task-Queue
  6. Jun 10, 2026
    Created url-shortner-typescript
  7. Jul 4, 2026
    Created AI-Interview-Coach
  8. Jul 7, 2026
    Created Build-a-Custom-Agent-Harness-from-scratch
  9. Jul 26, 2026
    Created neetcode-submissions — My NeetCode.io problem submissions
  10. Aug 9, 2026
    Created Incident-triage-agent
  11. Sep 4, 2026
    Created MusicBook — Generate Music Using AI and Voice
  12. Sep 4, 2026
    Most recent push to MusicBook

07 · Compare

github.com/
nikhil00shinde · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total51.4
Top-end curve+2.9
Final overall54.3

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.
nikhil00shinde · 54.3/100 — Rate My GitHub