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

#104 — Top 91.4%

LucasHJin

Lucas Jin

C

Getting there

Overall

0.0

/ 100

01 · Roasts

94% Python, 2% Everything Else

Your langPcts read like a Python supremacy manifesto. TypeScript at 2%, JavaScript at 2%, Swift clocking in at 1% — congrats on technically being 'multilingual' in the same way a tourist saying 'bonjour' is 'bilingual'.

684 Stars, No License

vit has 684 stars, install instructions, and people actively using it — but no open-source license. You've built the most popular unlicensed software since whatever that guy keeps on a USB drive.

Sprint God, Endurance Zero

bx-theory: 14 commits in 2 days. mfsn-map-mvp: 1 commit, created and pushed in 13 seconds. genai-testing: born and abandoned same afternoon. Your commit graph looks like a heart monitor for someone on espresso.

65 PRs, 1 Issue

You filed 65 external PRs this year but exactly 1 issue. Either every repo you touch is perfectly bug-free, or you're the type to silently fix things and never complain — which is either admirable or deeply repressed.

Graveyard-Free But Momentum-Challenged

Only 11% stale repos — impressive. But your heatmap has 4 full dead weeks and a suspicious blank row 10 and row 17. You're not abandoning projects, you're just… taking very meditative pauses between them.

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
    62C
  • Depth
    15% weight
    65C
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    50D

03 · Stats

365-day commit heatmap

172 active days

Less
More

Language distribution

7 langs
  • Python94%
  • TypeScript2%
  • JavaScript2%
  • Swift1%
  • CSS0%
  • PowerShell0%
  • Other1%

04 · Numbers

Owned repos

non-fork

37

Commits

last 12 months

810

Followers

109

Joined GitHub

Sep 2022

05 · Top repos

LucasHJin /

vit

60/100

Vit — a domain-specific version control system for video editing timelines. Serializes DaVinci Resolve timelines to domain-split JSON (cuts, color, audio, effects, markers), uses git as backend, and employs AI-assisted semantic merge resolution. Active project with 684 stars, comprehensive tests, structured codebase (1

I55Q65D50
READMETests
Python6841mo ago

LucasHJin /

obsidian-pets

54/100

TypeScript Obsidian plugin with 22 pet variants, animations, RAG chat integration, and physics-based ball interactions. Typed, documented, structured codebase with CI pipeline but no test suite.

I45Q65D50
READMECITyped
TypeScript321mo ago

LucasHJin /

portfolio-v2

45/100

Personal portfolio website showcasing multiple hackathon projects and side work. Typed Next.js app with API integration (Supabase), interactive pet animation component, and gym/weight tracking visualization via live Google Sheets.

I25Q60D50
READMETyped
TypeScript11mo ago

LucasHJin /

foodie

40/100

TypeScript Next.js nutrition tracker with force-directed graph visualization, USDA/Gemini integration. Fresh project (~1 day old), solid architecture, no tests/CI, good type coverage but incomplete feature set.

I25Q60D35
READMETyped
TypeScript02mo ago

LucasHJin /

ascii-experiment

38/100

Experimental React+TypeScript video-to-ASCII converter with two implementations (canvas and WebGL); minimal scope, 0 stars, 23/30 recent commits over 5 days, typed language with structured components but no tests, CI, or license.

I25Q55D35
READMETyped
TypeScript01mo ago

LucasHJin /

bx-theory

37/100

Experimental study planner using Google ADK multi-agent system to parse PDFs and generate spaced-repetition study schedules. Early-stage project with working agent architecture, no tests, minimal adoption, created 2 days ago.

I25Q50D35
README
Python03mo ago

LucasHJin /

LucasHJin

30/100

Personal portfolio README for CS student at UW with links to shipped projects (git video editor, obsidian plugin). Minimal repo content itself (24KB), but demonstrates active shipping across multiple real projects.

I40Q25D20
README
Unknown02mo ago

LucasHJin /

mfsn-map-mvp

13/100

Single-day MVP scaffolding for Mapbox-powered Svelte map with basic marker management. No README, tests, CI, or documentation. Minimal architectural scope with 18 KB codebase.

I5Q30D5
Typed
Svelte03mo ago

LucasHJin /

genai-testing

7/100

Empty scaffold created moments ago with 1 commit and 60KB total size. No README, tests, CI, or documentation. Minimal code footprint with no discernible project structure or functionality.

I5Q10D5
Unknown02mo ago

06 · Timeline

  1. Sep 1, 2022
    Joined GitHub
  2. Mar 21, 2024
    Created LucasHJin
  3. Jun 7, 2025
    Created obsidian-pets — Adds cute pixel pets to Obsidian.
  4. Dec 4, 2025
    Created portfolio-v2 — Revamped personal portfolio with more personal touches.
  5. Feb 4, 2026
    Created bx-theory
  6. Feb 8, 2026
    Created mfsn-map-mvp
  7. Mar 14, 2026
    Created vit — Git for video editing.
  8. Mar 14, 2026
    Created genai-testing
  9. Mar 16, 2026
    Created foodie — knowledge graph of food tracking 😋
  10. Apr 20, 2026
    Created ascii-experiment — Experimenting with creating a video to ascii component.
  11. Apr 25, 2026
    Most recent push to ascii-experiment

07 · Compare

github.com/
LucasHJin · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total62.6
Top-end curve+5.4
Final overall68.0

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.
LucasHJin · 68.0/100 — Rate My GitHub