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

#663 — Top 44.5%

jackliusr

Jack Liu Shurui

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

160 Repos, 8 Stars

You've accumulated 160 public repos over 15 years and netted a grand total of 8 stars. That's 0.05 stars per repo — technically not even a rounding error on the GitHub trending page.

The Empty 'ai' Repo

You created a repo literally called 'ai' on 2026-03-01 and pushed… nothing. Not a README, not a comment, not a hello world. The AI hype caught you mid-thought and you just left the oven on.

CI That Does Nothing

copilot-provider-4claude-code-router proudly sports a CI badge — but it's a copy-pasted SLSA3 boilerplate with placeholder artifacts and zero test coverage. That's not a pipeline, that's a decoration.

34 Public Commits in a Year

totalCommitsYear=34 means you averaged less than 3 commits per month publicly. The system charitably notes privateWorkLikely=true, so we can't fully roast you — but the public record is heroically quiet.

Certificates.git

Your 'certificates' repo is 16.5 MB of PDFs version-controlled in Git. You've essentially turned GitHub into a very slow, public filing cabinet for your LinkedIn achievements.

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
    60C
  • Quality
    20% weight
    22F
  • Depth
    15% weight
    55D
  • Breadth
    10% weight
    65C
  • Community
    10% weight
    40D

03 · Stats

365-day commit heatmap

80 active days

Less
More

Language distribution

7 langs
  • C#50%
  • Python23%
  • HTML7%
  • JavaScript7%
  • Gherkin6%
  • Jupyter Notebook2%
  • Other5%

04 · Numbers

Owned repos

non-fork

58

Commits

last 12 months

34

Followers

51

Joined GitHub

Apr 2009

05 · Top repos

jackliusr /

agents

38/100

Learning/exploration repository covering multiple agent frameworks (LangChain, CrewAI, Google ADK, Microsoft Agent Framework) with runnable examples but minimal documentation, no tests, and no license. Shows breadth of investigation but lacks production polish.

I25Q40D50
README
Python01mo ago

jackliusr /

copilot-provider-4claude-code-router

28/100

Personal setup helper for GitHub Copilot authentication and Claude Code Router integration, created 2026-03-18 with 3 commits. Addresses local configuration issues but lacks tests, comprehensive documentation, and production signals.

I25Q40D20
READMECI
JavaScript02mo ago

jackliusr /

jackliusr.github.io

23/100

Personal Hugo static site (github.io) with no documentation, tests, or CI. 30 recent commits over ~6 years show sustained personal use, but lacks production-ready structure and public utility.

I5Q20D45
HTML01mo ago

jackliusr /

ssh-pods

20/100

Minimal Kubernetes demo project with 4 YAML manifests (pods, service, kustomization) for SSH testing. Created and pushed on 2026-04-02 (same day), 8 KB total size, no tests or CI. Educational scaffold rather than reusable tool.

I15Q0D0
README
Unknown02mo ago

jackliusr /

aspx-in-linux

18/100

Minimal experimental ASP.NET todo app demonstrating Mono + Nginx containerization. Created 2026-04-03 with only 1 commit in ~4 minutes. No tests, CI, license, or meaningful scope validation. Works as proof-of-concept but lacks production polish.

I15Q35D5
README
ASP.NET02mo ago

jackliusr /

certificates

12/100

Personal certificate archive with minimal code—a collection of PDF links and credentials, no software artifacts, code structure, or active development beyond version control.

I5Q10D25
README
Unknown01mo ago

jackliusr /

jackliusr

12/100

Personal profile repo with minimal code substance—only a README listing technologies studied. No executable code, tests, CI, license, or production artifacts. 18 commits over 6+ years represent sporadic activity rather than sustained development.

I5Q15D20
README
Unknown01mo ago

jackliusr /

ai

2/100

Empty scaffold repo with zero content, no documentation, no code, and no activity. This is a placeholder initialization with no meaningful implementation.

I5Q0D5
Unknown03mo ago

06 · Timeline

  1. Apr 4, 2009
    Joined GitHub
  2. Jul 13, 2020
    Created jackliusr
  3. Aug 20, 2020
    Created jackliusr.github.io — my hugo site
  4. Jun 18, 2022
    Created certificates
  5. Mar 1, 2026
    Created ai
  6. Mar 18, 2026
    Created copilot-provider-4claude-code-router
  7. Apr 2, 2026
    Created ssh-pods — ssh client and server pods with key configurations, authorized_keys to demo how to make it work in kubernetes environment
  8. Apr 3, 2026
    Created aspx-in-linux — aspx todo app in linux container
  9. Apr 19, 2026
    Created agents — learning on agents related topics
  10. Apr 27, 2026
    Most recent push to jackliusr.github.io

07 · Compare

github.com/
jackliusr · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total43.4
Top-end curve+1.4
Final overall44.8

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.
jackliusr · 44.8/100 — Rate My GitHub