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

#405 — Top 66.1%

Jeremy-Qian

Jeremy-Qian

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

Serial IDE Starter

You've built JereIDE AND JereIDE_wx — two separate code editors — yet neither has shipped to a single real user. Pick one and finish it before the third IDE shows up.

The Heatmap Winter

Weeks 3–23 of your heatmap are basically a tundra. 568 commits in a year sounds decent until you realize half of them happened in the last 6 weeks. Consistency is not a sprint.

1+1=2 Is Not a Test Suite

jerenotes has HAS_TESTS=yes — impressive, until you read that the entire test is 'assert 1 + 1 == 2'. That's not testing your app, that's testing arithmetic.

README? Never Heard of Her

5 out of 9 analyzed repos have no README. You're a CEO who can't document what his company makes. RampageBot, RampChat, wake-up-streamlit, jeremy-qian.github.io — all launched naked into the world.

41 PRs, 3 Followers

You've opened 41 pull requests this year on other people's code — genuinely active in the open-source world — yet only 3 people follow you. The networking is not matching the output.

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
    33F
  • Consistency
    20% weight
    65C
  • Quality
    20% weight
    57D
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    40D

03 · Stats

365-day commit heatmap

89 active days

Less
More

Language distribution

5 langs
  • Python42%
  • HTML32%
  • TeX25%
  • C++1%
  • CSS0%

04 · Numbers

Owned repos

non-fork

14

Commits

last 12 months

568

Followers

3

Joined GitHub

Mar 2025

05 · Top repos

Jeremy-Qian /

JereIDE_wx

45/100

AI-assisted wxPython IDE with functional editor, multi-tab notebook, file I/O, and Python syntax highlighting. Typed Python, well-documented, structured architecture. Early-stage experimental project with macOS CI.

I25Q60D50
READMETestsCI
Python11mo ago

Jeremy-Qian /

JereIDE

35/100

Beta-stage Python code editor built on PySide6 with native macOS integration. Typed Python, structured multi-file layout, and comprehensive config system. Early-stage indie project with limited adoption (2 stars, beta status).

I25Q50D35
READMECI
Python28d ago

Jeremy-Qian /

jerechat

35/100

Personal Streamlit chatbot project with A/B testing infrastructure, PyTorch-based response generation, and Supabase integration. Early-stage application with functional feature set but lacks tests, CI/CD, and type hints in Python code.

I25Q45D35
README
Python121d ago

Jeremy-Qian /

RampageBot

20/100

A beginner chatbot project for "The Rampage" newspaper, built with TF-IDF and NLTK. Minimal documentation, no tests, no CI, no license. 8 days old with 30 commits in a short burst.

I15Q25D20
Python113d ago

Jeremy-Qian /

wake-up-streamlit

20/100

Minimal personal Streamlit project with no README, no tests, no license, and only 5 KB of code. Recent CI presence suggests active tinkering but lacks documentation and structure for meaningful adoption.

I15Q25D20
CI
Python121d ago

Jeremy-Qian /

jerenotes

18/100

Fresh Briefcase-scaffolded wrapper app around manifest.app webview. One commit, 1 star, minimal logic, placeholder test. Designed but not shipped as a real product.

I15Q35D5
READMETests
Python12mo ago

Jeremy-Qian /

jeremy-qian.github.io

10/100

Personal GitHub Pages site with minimal content; 75 KB HTML repo, 1 star, no README, docs, tests, or CI. Appears to be a nascent portfolio scaffold.

I5Q10D15
HTML116d ago

Jeremy-Qian /

Jeremy-Qian

8/100

Profile README repo with minimal content (3 KB, no files), auto-generated GitHub streak badge, and contact email. No functional code, tests, or documentation beyond a profile display template.

I5Q10D5
README
Unknown115d ago

Jeremy-Qian /

RampChat

7/100

Empty scaffold with minimal viable Python project structure. Created and pushed same day with 1 commit. No README, tests, CI, or meaningful code—classic one-shot dump lacking any documentation or substance.

I5Q10D5
Python13mo ago

06 · Timeline

  1. Mar 8, 2025
    Joined GitHub
  2. May 10, 2025
    Created Jeremy-Qian — Config files for my GitHub profile.
  3. Nov 17, 2025
    Created jeremy-qian.github.io
  4. Nov 17, 2025
    Created jerechat
  5. Feb 23, 2026
    Created wake-up-streamlit
  6. Mar 2, 2026
    Created RampChat
  7. Mar 12, 2026
    Created jerenotes — A simple note app that is built on Toga/Briefcase.
  8. Apr 17, 2026
    Created JereIDE_wx
  9. Apr 28, 2026
    Created JereIDE — The fast simple code editor, in progress and in beta, built with PyObjC, Pyte, and PySide6
  10. May 13, 2026
    Created RampageBot
  11. May 26, 2026
    Most recent push to JereIDE

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 total50.8
Top-end curve+2.9
Final overall53.7

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.
Jeremy-Qian · 53.7/100 — Rate My GitHub