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

#475 — Top 72.6%

Jeremy-Qian

Jeremy Qian

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

Commit confetti cannon

656 yearly commits and 171 multi-repo volume say you ship constantly; tests and CI missed the invite on nearly every repo.

One-star constellation

12 scored repositories account for 15 total stars and 0 forks—lots of launches, almost no orbital pull.

Single-file boss rush

Ramp-Monopoly, DigitalClock, and Ramp-Website-New put serious ambition into index.html, then leave architecture in the loading screen.

Chatbot multiverse

RampageBot, jerechat, and RampChat give you three routes to conversational AI; automated regression coverage gives you zero.

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
    38F
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    25F

03 · Stats

365-day commit heatmap

172 active days

Less
More

Language distribution

6 langs
  • Python50%
  • HTML44%
  • C++4%
  • Rust1%
  • CSS0%
  • Other1%

04 · Numbers

Owned repos

non-fork

15

Commits

last 12 months

656

Followers

6

Joined GitHub

Mar 2025

05 · Top repos

Jeremy-Qian /

RampageBot

41/100

A small deployed Streamlit chatbot for The Rampage, using NLTK preprocessing and scikit-learn TF-IDF similarity, with a named public domain but limited adoption and no testing or CI.

I35Q40D50
README
Python125d ago

Jeremy-Qian /

Hangman

39/100

A small, documented Rust CLI Hangman game with basic modular functions and random word selection; it has MIT licensing and GitHub Actions automation, but little adoption and limited project scope.

I20Q52D45
READMECITyped
Rust123d ago

Jeremy-Qian /

jerechat

37/100

A documented Streamlit chatbot with PyTorch response generation, invitation access, Supabase feedback, and A/B model comparison; it is a small 1-star project without tests or CI.

I20Q42D50
README
Python12mo ago

Jeremy-Qian /

HitTheGiant

35/100

A documented but small C++ terminal game with two modes, randomized giants, inventory, rewards, and a single-file implementation; it lacks tests, CI, and a license.

I20Q35D50
README
C++126d ago

Jeremy-Qian /

DigitalClock

34/100

A small, deployed fullscreen clock with configurable visual controls and Wikimedia background search, but adoption and engineering scope remain limited.

I30Q35D35
README
HTML123d ago

Jeremy-Qian /

Ramp-Monopoly

32/100

A small, playable two-player Monopoly web game implemented in a single index.html, with canvas board rendering, dice, properties, money, turns, and themed UI, but limited documentation and engineering safeguards.

I20Q40D35
README
HTML11mo ago

Jeremy-Qian /

rampwebsite

30/100

A small Streamlit website with navigation, informational pages, a local-storage poll demo, and a bundled Tkinter sample app; it is documented but lacks adoption signals, tests, CI, and production backend integration.

I20Q38D35
README
Python127d ago

Jeremy-Qian /

20-Questions

27/100

A functional MIT-licensed Python CLI Twenty Questions game in main.py, with JSON-backed learning and a clear README, but no tests, CI, or typed structure and minimal demonstrated adoption.

I20Q35D25
README
Python126d ago

Jeremy-Qian /

jeremy-qian.github.io

27/100

A small, polished personal portfolio site with a focused HTML/CSS implementation, three linked projects, and minimal repository infrastructure or adoption.

I22Q38D20
README
HTML12mo ago

Jeremy-Qian /

RampChat

25/100

Small Streamlit/Supabase group-chat template with login, avatars, message persistence, and theming, but it is explicitly experimental and its database is shut down.

I15Q40D20
README
Python12mo ago

Jeremy-Qian /

Jeremy-Qian

22/100

A personal GitHub profile configuration repository with a styled README and identity badges, but no source files, tests, CI, license, or demonstrated external adoption.

I15Q25D35
README
Unknown11mo ago

Jeremy-Qian /

Ramp-Website-New

20/100

A small, documented MIT-licensed HTML redirect page with a polished loading animation and fallback links, but no tests, CI, typed code, or evidence of meaningful external adoption.

I15Q35D20
README
HTML126d ago

06 · Timeline

  1. Mar 8, 2025
    Joined GitHub
  2. Mar 8, 2025
    Created rampwebsite — Ramp website
  3. Mar 17, 2025
    Created HitTheGiant — A C++ Game that.. lets you hit giants.
  4. May 10, 2025
    Created Jeremy-Qian — Config files for my GitHub profile.
  5. Oct 11, 2025
    Created Ramp-Website-New — Nothing. redirects to the-rampage.weebly.com
  6. Nov 17, 2025
    Created Ramp-Monopoly — A Ramp-themed Monopoly Game.
  7. Nov 17, 2025
    Created jeremy-qian.github.io — Personal website, of course.
  8. Nov 17, 2025
    Created jerechat — JereChat, just a chatbot.
  9. Dec 17, 2025
    Created 20-Questions — A simple Twenty Questions game, with Rampions.
  10. Mar 2, 2026
    Created RampChat — Template for hosting your own streamlit social media server.
  11. May 13, 2026
    Created RampageBot — Science Fair Project. Integrated at rampage.is-great.org
  12. Jun 28, 2026
    Created Hangman — A simple hangman game in Rust.
  13. Aug 3, 2026
    Created DigitalClock — Because the digital clocks online are paid and are bad, I decided to make one myself. CAUTION- Completely dominated by AI code.
  14. Aug 28, 2026
    Most recent push to DigitalClock

07 · Compare

github.com/
Jeremy-Qian · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total54.3
Top-end curve+3.6
Final overall57.9

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.
Jeremy-Qian · 57.9/100 — Rate My GitHub