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

#56 — Top 95.4%

joyehuang

De-Shiou Huang

B

Solid engineer

Overall

0.0

/ 100

01 · Roasts

Launch-Day Larry

Learn-Open-Harness (317 stars) and OpenHarness-notes (7845KB, 114 tests) were both created AND last-pushed on the same day as their parent projects. Shipping fast is a skill; shipping *only* fast is a pattern.

Test Allergist

10 out of 12 repos have HAS_TESTS=no. You wrote 114 tests for OpenHarness-notes in one afternoon but couldn't find time for a single pytest in mind-ai-quest, blog, coding-agent, or components-lib. Selective diligence is still a gap.

CI Ghost

Only 2 repos (minimind-notes, joyehuang) have CI configured. You're deploying to Vercel, ModelScope, and GitHub Pages but running no automated pipelines on 10/12 repos. Hope nothing breaks on merge.

Heatmap Hibernator

Your commit heatmap is a flatline for the first 34 weeks of the year, then a frantic sprint. 690 commits squeezed into ~18 weeks looks less like 'engineer' and more like 'semester project panic mode.'

Star Imbalance

317 of your 431 total stars live in a single repo. Strip Learn-Open-Harness and you have 114 stars across 42 repos — that's 2.7 stars per repo. The portfolio is wide but the impact is a single point of gravity.

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
    69C
  • Depth
    15% weight
    65C
  • Breadth
    10% weight
    72B
  • Community
    10% weight
    55D

03 · Stats

365-day commit heatmap

133 active days

Less
More

Language distribution

7 langs
  • JavaScript52%
  • Python29%
  • TypeScript13%
  • Java2%
  • HTML1%
  • CSS1%
  • Other2%

04 · Numbers

Owned repos

non-fork

35

Commits

last 12 months

690

Followers

50

Joined GitHub

Sep 2023

05 · Top repos

joyehuang /

Learn-Open-Harness

60/100

Interactive educational tutorial for OpenHarness built with Next.js 16 + TypeScript. 12 chapters with animated diagrams, quizzes, and interactive simulators. Launched day-after OpenHarness release, shipped with clean structure and bilingual i18n support. No CI/tests but well-documented with meaningful project architect

I55Q60D65
READMETyped
TypeScript3171mo ago

joyehuang /

minimind-notes

59/100

Educational LLM training tutorial with modular experiments. Typed Python (PyTorch), extensive docs (docs/, design.md, ARCHITECTURE.md), CI/CD (HAS_CI=yes), good code structure. 100 stars, ~30 commits last 6mo, 35MB codebase. Clear educational mission but narrow audience impact.

I55Q72D50
READMECITyped
Python1001mo ago

joyehuang /

mind-ai-quest

55/100

Educational interactive web app with Next.js + Three.js 3D scenes teaching ML concepts via gamified rice-farming metaphor. Well-typed TypeScript, structured components, good UX design, but no tests/CI and minimal external adoption signals (1 star, 0 followers visible).

I35Q65D60
READMETyped
TypeScript12mo ago

joyehuang /

blog

48/100

Personal Astro blog with TypeScript, React interactive terminal, dynamic OG generation. Clean typed architecture, minimal stars/forks; shipped working portfolio site—typical active student project with structured layout and meaningful features.

I25Q60D50
READMETyped
Astro01mo ago

joyehuang /

pydantic-agent-benchmark

40/100

Experimental benchmark tool comparing schema-constrained LLM outputs using Pydantic. Early-stage project with clear structure (typed Python, React frontend, mock tools, two benchmark phases), but incomplete execution (runner.py truncated mid-function, no tests/CI, 0 stars).

I25Q60D35
READMETyped
Python01mo ago

joyehuang /

coding-agent

40/100

TypeScript template for AI-powered coding agents supporting Claude, OpenAI Codex, GitHub Copilot, Cursor, Gemini, and opencode. Multi-agent SaaS scaffolding with Vercel Sandbox integration, PostgreSQL persistence, OAuth2 auth, and MCP server support. Very young repo (3 days old, 4 commits) with minimal evidence of sust

I25Q60D35
READMETyped
TypeScript12mo ago

joyehuang /

components-lib

37/100

Early-stage Next.js component library with TypeScript, structured layout, and documented components (blur-highlight). Active recent commits (18/30), but no tests, CI, or license. Minimal adoption (0 stars). Mirrors shadcn/ui pattern with CLI aspirations still in design phase.

I25Q50D35
READMETyped
TypeScript03mo ago

joyehuang /

OpenHarness-notes

35/100

Early-stage AI agent framework with 43 tools, extensive documentation, and test coverage. Created and pushed within hours (Apr 12, 2026), unproven adoption but structured architectural scope and typed Python codebase with meaningful docs justify mid-tier quality baseline.

I25Q60D20
READMETests
Python01mo ago

joyehuang /

joyehuang

35/100

Personal profile config repo with README showcasing student projects and experience. Minimal codebase (30KB), no tests or license, but documents portfolio work in AI/full-stack development with links to featured projects.

I25Q45D35
READMECI
Unknown33mo ago

joyehuang /

desk-widget

28/100

Personal macOS desktop widget for Übersicht displaying WakaTime and GitHub daily stats. Well-documented setup but minimal scope, 0 stars, created 2 days ago with 3 commits total. Meets baseline typed+documented standard.

I15Q50D20
README
Shell02mo ago

joyehuang /

sbit-en

20/100

Mirror/clone of SBTI test with separated images and HTML. Minimal documentation (3-line README in Chinese), no tests/CI, zero stars/forks, 6 commits over ~5 hours. Appears to be a one-off personal project or tutorial fork.

I15Q25D20
README
HTML01mo ago

joyehuang /

skills

10/100

Minimal Python project with 1 star, no README, tests, CI, license, or documentation. 5 commits over ~2 months with no typed code or structured architecture visible. Appears to be an early-stage experimental scaffold.

I5Q10D20
Python11mo ago

06 · Timeline

  1. Sep 4, 2023
    Joined GitHub
  2. Nov 19, 2024
    Created joyehuang — Config files for my GitHub profile.
  3. Oct 23, 2025
    Created blog — joye's personal blog
  4. Nov 8, 2025
    Created minimind-notes — 🚀 [从零构建 LLM] 极简大模型训练原理与实践指南。包含 Transformer, Pretraining, SFT 核心代码与对照实验。 | A minimal, principle-first guide to understanding and building LLMs from scratch.
  5. Feb 6, 2026
    Created mind-ai-quest
  6. Feb 13, 2026
    Created skills
  7. Feb 24, 2026
    Created components-lib
  8. Mar 11, 2026
    Created desk-widget
  9. Mar 22, 2026
    Created coding-agent
  10. Apr 6, 2026
    Created pydantic-agent-benchmark
  11. Apr 7, 2026
    Created Learn-Open-Harness — 🤖 Official Interactive Tutorial for OpenHarness – Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | 面向零基础的 AI Agent 交互式教程
  12. Apr 10, 2026
    Created sbit-en
  13. Apr 12, 2026
    Created OpenHarness-notes
  14. Apr 28, 2026
    Most recent push to blog

07 · Compare

github.com/
joyehuang · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total66.3
Top-end curve+5.8
Final overall72.1

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.
joyehuang · 72.1/100 — Rate My GitHub