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

#301 — Top 74.9%

Himanshu197200

Himanshu Mishra

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

87% Jupyter, 0% Production

Your language breakdown is 87% Jupyter Notebook. That's not a language distribution, that's a homework submission queue. Even your 'ML system' repos are essentially executed essays.

Sprint God, CI Atheist

Not a single repo across 8 analyzed has a CI pipeline. Zero. You've shipped state machines, LLM agents, and RBAC systems but apparently draw the line at a 5-line GitHub Actions YAML.

genyx-poc: World Record Auth Service

You built a JWT+OAuth service in 39 minutes flat and called it a day. The repo was born and abandoned before most people finish their morning coffee. 27KB of ambition.

0 Followers, 16 PRs, All Solo

soloPct=100% means every one of those 16 PRs this year was you talking to yourself. You've mastered the art of the one-person code review. Deeply committed to the echo chamber.

Scratch_that_Code: Commitment Issues

Scratch_that_Code was initialized in literally 1 second and never touched again. At least name it honestly — 'scratch_that_idea.md' would have been more accurate.

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
    65C
  • Quality
    20% weight
    62C
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    25F

03 · Stats

365-day commit heatmap

93 active days

Less
More

Language distribution

6 langs
  • Jupyter Notebook87%
  • JavaScript8%
  • TypeScript2%
  • CSS1%
  • Python1%
  • HTML1%

04 · Numbers

Owned repos

non-fork

31

Commits

last 12 months

360

Followers

0

Joined GitHub

Oct 2024

05 · Top repos

Himanshu197200 /

Smart_Garage_Seva

52/100

TypeScript automotive service platform with state machine job workflow, role-based access (Admin/Mechanic/Customer), predictive maintenance via strategy pattern, and React/Express full-stack. 30 commits across ~2.5 months, 2445 KB codebase, comprehensive documentation but no CI/CD.

I40Q65D50
READMETestsTyped
TypeScript01mo ago

Himanshu197200 /

AI_Health_Risk_System

50/100

End-semester healthcare ML project combining 5 regression models with Streamlit dashboard, agentic LLM reporting, and PDF export. Typed Python, structured src/ layout, comprehensive README with live deployment, but no CI, no license, and minimal test coverage (3 unit tests).

I40Q60D50
READMETests
Jupyter Notebook11mo ago

Himanshu197200 /

Turing_BroCodes_Student-Mental-Health-and-Burnout

41/100

Student mental health data analysis project with 1M-row dataset, Tableau dashboards, and structured documentation (design.md, ARCHITECTURE.md). Academic capstone (Newton School) with 30 commits in 2 days, no tests/CI, untyped Jupyter notebooks.

I25Q55D45
README
Jupyter Notebook01mo ago

Himanshu197200 /

Data_Table_for_AI_Dashboard

28/100

Fresh React + Vite + Tailwind dashboard for tabular data display. Untyped JavaScript with good component structure (custom hooks, modular components), documented README, and ESLint setup—but no tests, CI, or type safety. Experimental personal project, 1 day old.

I15Q50D20
README
JavaScript03mo ago

Himanshu197200 /

CLI_TOOL_PROJECT

27/100

TypeScript CLI tool with ~17 command implementations using Commander.js and OOP patterns. No tests, CI, or license; created and last pushed same day (2026-03-04). Instructional personal project with basic math and API integrations.

I15Q45D20
READMETyped
TypeScript03mo ago

Himanshu197200 /

genyx-poc

15/100

Early-stage TypeScript auth service POC with JWT+OAuth routes, minimal docs, no tests/CI. Created and pushed same day (2 of 30 recent commits). Typed + structured but thin documentation and single-week sprint scope.

I5Q40D5
READMETyped
TypeScript015d ago

Himanshu197200 /

streamlit-html-demo

7/100

Empty scaffold with 6KB of code, no README, no tests, no CI, created and last pushed same day. Appears to be a one-off experimental dump.

I5Q10D5
Python01mo ago

Himanshu197200 /

Scratch_that_Code

7/100

Empty scaffold repo created moments ago with minimal README and no code. Zero stars, no commits beyond initial, and unknown language indicate this is a placeholder project.

I5Q10D5
README
Unknown03mo ago

06 · Timeline

  1. Oct 11, 2024
    Joined GitHub
  2. Feb 15, 2026
    Created AI_Health_Risk_System
  3. Feb 18, 2026
    Created Smart_Garage_Seva
  4. Feb 26, 2026
    Created Scratch_that_Code
  5. Feb 27, 2026
    Created Data_Table_for_AI_Dashboard
  6. Mar 4, 2026
    Created CLI_TOOL_PROJECT
  7. Apr 7, 2026
    Created streamlit-html-demo
  8. Apr 27, 2026
    Created Turing_BroCodes_Student-Mental-Health-and-Burnout
  9. May 19, 2026
    Created genyx-poc
  10. May 19, 2026
    Most recent push to genyx-poc

07 · Compare

github.com/
Himanshu197200 · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total54.1
Top-end curve+3.6
Final overall57.7

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.
Himanshu197200 · 57.7/100 — Rate My GitHub