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

#601 — Top 66.0%

ibrahimhabibeg

Ibrahim Habib

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

Notebook monoculture

98% of the language mix is Jupyter Notebook: the repos are doing science, but the language chart is doing a solo performance.

CI sighting

diffusion-brain-alignment-blog has GitHub Pages CI; the other four scored repos apparently left automation at the lab door.

Validation vacuum

Five scored repos, zero with tests, and zero with licenses: reproducibility is carrying the whole group project.

Pipeline-rich, adoption-poor

Snakemake, LSDB, Stable Diffusion, Gemini, and Gradio all appear—yet the scored repos collectively show 0 stars.

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
    48D
  • Consistency
    20% weight
    60C
  • Quality
    20% weight
    52D
  • Depth
    15% weight
    55D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    40D

03 · Stats

365-day commit heatmap

237 active days

Less
More

Language distribution

6 langs
  • Jupyter Notebook98%
  • TypeScript1%
  • Python1%
  • C++0%
  • JavaScript0%
  • TeX0%

04 · Numbers

Owned repos

non-fork

41

Commits

last 12 months

282

Followers

49

Joined GitHub

Jul 2020

05 · Top repos

ibrahimhabibeg /

spectra-captioning

38/100

A documented Python astronomy pipeline with four CLI entry points, LSDB catalog crossmatching, FastSpecFit extraction, spectrum plotting, and Gemini multimodal caption strategies; substantial implementation is offset by absent tests, CI, license, and visible runtime defects.

I20Q55D35
README
Python★ 02mo ago

ibrahimhabibeg /

diffusion-brain-alignment-blog

38/100

A substantial Quarto research manuscript comparing Stable Diffusion and macaque ventral-stream representations, with reproducible RSA methodology and GitHub Pages publishing, but no visible adoption, tests, license, or typed implementation.

I20Q45D50
CI
Jupyter Notebook★ 02mo ago

ibrahimhabibeg /

diffusion-brain-alignment

34/100

A documented, non-trivial Neuromatch Academy research pipeline combining Snakemake, Stable Diffusion feature extraction, macaque data processing, RSA statistics, bootstrapping, and visualization, but with no demonstrated adoption or validation infrastructure.

I20Q45D35
README
Python★ 03mo ago

ibrahimhabibeg /

spectra-captions-viewer

27/100

A documented, multi-file Gradio astronomy evaluator with interactive spectra, evidence quotes, and feedback persistence; it shows practical implementation but no tests, CI, typing, license, or demonstrated external adoption.

I20Q40D20
README
Python★ 02mo ago

ibrahimhabibeg /

direct-diffusion

20/100

A one-day, zero-star educational Marimo notebook explaining direct data prediction in diffusion models, with a toy implementation scaffold but no documentation, tests, CI, or packaging.

I15Q25D20
Python★ 04mo ago

06 · Timeline

  1. Jul 12, 2020
    Joined GitHub
  2. Jun 28, 2026
    Created direct-diffusion
  3. Jul 16, 2026
    Created diffusion-brain-alignment — A study of the representational alignment between diffusion models and Macaque cross timesteps and ROIs
  4. Jul 23, 2026
    Created diffusion-brain-alignment-blog
  5. Aug 9, 2026
    Created spectra-captioning
  6. Aug 9, 2026
    Created spectra-captions-viewer
  7. Aug 29, 2026
    Most recent push to spectra-captioning

07 · Compare

github.com/
ibrahimhabibeg · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total52.1
Top-end curve+3.1
Final overall55.3

Tier thresholds

S90–100Mass-producing humansA80–89Ship machineB70–79Solid engineerC60–69Getting thereD40–59README enthusiastF0–39GitHub 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.
ibrahimhabibeg · 55.3/100 — Rate My GitHub