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

#233 — Top 80.6%

tristanth03

Tristan Þórðarson

C

Getting there

Overall

0.0

/ 100

01 · Roasts

README.md: 'Bob'

NTK's entire README is the word 'Bob'. Not 'Bob — a tool for X'. Just... Bob. This is not documentation, this is a hostage note with no ransom demand.

ClaudeTest: 0 KB of ambition

ClaudeTest is a 0 KB repo with a 2-line README that says 'Save Space'. You pushed an empty folder to GitHub and called it a day. The cloud does not need your vibes.

The Great Commit Desert

Your heatmap has a 35-week dead zone in the middle — weeks 8 through 40 are essentially barren tundra. You vanished from GitHub for most of the year, then came back in a flurry. Consistency is not a concept you two have met.

43 PRs, 4 Followers

You've opened 43 pull requests this year but accumulated only 4 followers. Either you're contributing to projects in total silence or everyone politely ignores your PRs. Either way, the ratio is haunting.

100% Solo, 0% Tests

soloPct = 100% and not a single repo has tests. You are a lone wolf who also never double-checks anything. ETH has 37 MB of MATLAB coursework with no test suite — even academics write unit tests.

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
    56D
  • Consistency
    20% weight
    65C
  • Quality
    20% weight
    52D
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    65C
  • Community
    10% weight
    40D

03 · Stats

365-day commit heatmap

69 active days

Less
More

Language distribution

6 langs
  • HTML65%
  • Jupyter Notebook32%
  • Python3%
  • Julia0%
  • MATLAB0%
  • JavaScript0%

04 · Numbers

Owned repos

non-fork

12

Commits

last 12 months

280

Followers

4

Joined GitHub

Feb 2023

05 · Top repos

tristanth03 /

TBMRS

40/100

Movie recommendation system with typed Python backend (recommender.py, api_wrapper__v00.py), Firebase Firestore integration, and HTML/JS frontend. Minimal GitHub presence (0 stars, <30 days old) but ships structured codebase with incomplete docs and no tests.

I25Q50D35
README
HTML02mo ago

tristanth03 /

math_slime

38/100

A 2-day-old math education game for kids with clean HTML5 canvas engine, pre-generated problem pools via Python, Firebase auth/leaderboard, and thoughtful design docs. Single-developer personal project shipping on GitHub Pages.

I20Q50D45
README
Jupyter Notebook01mo ago

tristanth03 /

MIP

38/100

Static site for searchable HTML report archival with Python build automation and GitHub Pages CI. Minimal scope, recent creation (2 days old), but well-structured tooling and consistent theme system.

I25Q55D35
READMECI
HTML01mo ago

tristanth03 /

UNC

38/100

Notebook-to-HTML converter (v0.3/v0.4) with math support, theme system, and Jupyter introspection. Typed Python, clean architecture, functional but minimal documentation; <2 weeks active development.

I25Q55D35
README
HTML01mo ago

tristanth03 /

ETH

30/100

Educational coursework repository collecting ETH student projects (MATLAB statistical analysis, Python ML/finance, R notebooks) across multiple quantitative programs. Lacks documentation, structure, versioning discipline, and real production intent.

I15Q35D40
README
Jupyter Notebook01mo ago

tristanth03 /

NA-SkiResort-SnowyCities

28/100

Early-stage hobby project with minimal output (0 stars, 7 commits in 1 day). Has documentation files and MIT license, but no functional code sampled and no tests/CI. Untyped language with very recent creation (April 2026).

I15Q45D20
README
Unknown01mo ago

tristanth03 /

Project-MC-Blue

27/100

Early-stage Minecraft mod logger written in Java for capturing player telemetry (position, inventory, visible blocks/mobs). Basic Fabric mod structure with gradle CI but lacks README, tests, documentation, and has incomplete source files.

I15Q35D30
Typed
Java03mo ago

tristanth03 /

ClaudeTest

7/100

Empty scaffold with minimal README ("Save Space"); 0 KB, single commit, no code files, no tests, CI, or license. Appears to be a placeholder/experiment.

I5Q10D5
README
Unknown02mo ago

tristanth03 /

NTK

7/100

Minimal one-day-old repo with only a README containing "Bob", no source files visible, no tests/CI/license, and unknown language. Appears to be an empty scaffold or placeholder.

I5Q10D5
README
Unknown03mo ago

06 · Timeline

  1. Feb 13, 2023
    Joined GitHub
  2. Oct 1, 2025
    Created ETH — All projects at MSQF
  3. Feb 9, 2026
    Created NTK
  4. Feb 10, 2026
    Created Project-MC-Blue
  5. Mar 11, 2026
    Created ClaudeTest — Save Space
  6. Mar 22, 2026
    Created TBMRS — The Best Movie Recommendation System
  7. Apr 3, 2026
    Created UNC
  8. Apr 3, 2026
    Created MIP
  9. Apr 4, 2026
    Created math_slime
  10. Apr 9, 2026
    Created NA-SkiResort-SnowyCities
  11. Apr 24, 2026
    Most recent push to ETH

07 · Compare

github.com/
tristanth03 · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total56.6
Top-end curve+4.1
Final overall60.7

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.
tristanth03 · 60.7/100 — Rate My GitHub