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

#314 — Top 78.1%

dileeme

dilen shankar

C

Getting there

Overall

0.0

/ 100

01 · Roasts

The One-Star Millionaire

After 28 repos and nearly 2 years on GitHub, you've accumulated exactly 1 star — and it's on your profile README. The actual research projects with 300 FHE experiments? Zero stars. Your bio page is your magnum opus.

CI? Never Heard of Her

Zero repos have CI. Zero. You're submitting work to IEEE BIBM and BMC Bioinformatics with no automated tests or pipelines, just vibes and manually-run scripts. Reviewers can't reproduce your results but neither can you, probably.

The Deadline Sprint Archaeologist

MethCLR: 30 commits in 28 days then silence. LarpSuite: 4 commits in 6 hours. TwinVEIL: empty modules, 4 commits, IEEE GLOBECOM listed in the README. Your git history reads like a series of all-nighters with no morning after.

License-Free Zone

Almost every repo — including ones you're submitting to academic conferences — has no license. MethCLR, CKKS-BFV, GenomicBeaconsUnderSiege: all legally unreusable. You're publishing encrypted genomics research that nobody is legally allowed to build on.

Half-Baked Scaffold Collection

PassiveScanner (74 words, 5 KB, no code), ApexLab-source (bare HTML title), TwinVEIL (empty module files). Nearly a third of your repos are skeletons wearing READMEs as costumes. Ghost towns with good names.

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
    62C
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    25F

03 · Stats

365-day commit heatmap

71 active days

Less
More

Language distribution

7 langs
  • Python51%
  • Jupyter Notebook38%
  • C6%
  • HTML2%
  • CSS1%
  • R1%
  • Other1%

04 · Numbers

Owned repos

non-fork

25

Commits

last 12 months

314

Followers

1

Joined GitHub

Sep 2024

05 · Top repos

dileeme /

CKKS-BFV_TradeoffAnalysis_On_RNA-Seq

52/100

Rigorous FHE benchmarking of BFV vs CKKS on RNA-Seq differential expression scoring with 16.6 MB codebase, systematic experimental design, and comprehensive latency/accuracy tradeoff analysis across 300 runs and 2 datasets.

I40Q60D55
README
Python1this week

dileeme /

GenomicBeaconsUnderSiege

48/100

IEEE BIBM 2026 submission on privacy re-identification risk in genomic beacons using IBD-assisted MIA and FHE performance overhead. Research codebase with structured experiments, typed Python, tests, and detailed README. 0 stars suggests pre-publication/nascent dissemination.

I25Q65D55
READMETests
Python09d ago

dileeme /

MethCLR

42/100

A research project implementing contrastive learning for DNA methylation (EWAS). Contains typed Python code, structured architecture, meaningful README with method details, but no tests, CI, or license. Submitted to IEEE BIBM 2026; unproven adoption with 0 stars and recent creation (28 days old).

I25Q55D50
README
Python02mo ago

dileeme /

bioinformatics-workups

25/100

Learning resource for bioinformatics algorithms in Jupyter Notebooks; no tests, CI, license, or gitignore; minimal adoption (0 stars/forks); README present but vague about structure.

I15Q25D35
README
Jupyter Notebook0this week

dileeme /

TwinVEIL

25/100

Unfinished research framework for 6G Digital Twins with CKKS homomorphic encryption; README well-structured but core modules empty (client/encryptor.py, server modules are blank); 4 commits in ~3 months, no tests/CI, no license.

I15Q35D25
README
Python0this week

dileeme /

CRISMA

25/100

One-week sprint React/Three.js PDB molecule viewer. TypeScript + Vite template with no tests/CI, minimal commits, and experimental scope. Lacks production polish or external adoption.

I15Q40D20
READMETyped
TypeScript019d ago

dileeme /

LarpSuite

23/100

LarpSuite is a tkinter-based web penetration testing proxy/toolkit with HTTP interception, active scanning, intruder payload engine, repeater, and code analyzer modules. Untyped Python, no README/tests/CI/license, 4 recent commits over <1 day, 578 KB (~11k LOC) with ambitious scope but immature execution.

I15Q35D20
Python02mo ago

dileeme /

dileeme

20/100

GitHub profile configuration repo with README-only presence; 59 KB, no meaningful code or documentation structure beyond personal bio. 30 commits over ~17 months suggest periodic updates but minimal substantive work.

I5Q25D35
README
Unknown0this week

dileeme /

ApexLab-source

7/100

Minimal HTML scaffold with bare README title only, 5 commits in 4 days, no tests, CI, license, or meaningful documentation. Appears to be early-stage experimental work.

I5Q10D5
README
HTML020d ago

dileeme /

PassiveScanner

7/100

Empty scaffold project with only a README stub (74 words). No source files, no tests, no CI, no license, no gitignore. 5KB size confirms minimal/placeholder state. Created June 2026, 5 commits across 23 days.

I5Q10D5
README
Unknown01mo ago

06 · Timeline

  1. Sep 6, 2024
    Joined GitHub
  2. Mar 10, 2025
    Created dileeme — Config files for my GitHub profile.
  3. Mar 20, 2025
    Created bioinformatics-workups — A collection of bioinformatics algorithms implemented in Python, covering a range of computational techniques for analyzing biological data. This repository serves as a learning re
  4. Feb 25, 2026
    Created CKKS-BFV_TradeoffAnalysis_On_RNA-Seq
  5. Apr 3, 2026
    Created GenomicBeaconsUnderSiege — Quantifying Re-Identification Risk from Summary Statistics and the Performance Cost of Homomorphic Encryption
  6. Jun 1, 2026
    Created MethCLR — A contrastive learning framework for pipeline-invariant DNA methylation representations in Epigenome-Wide Association Studies (EWAS).
  7. Jun 1, 2026
    Created TwinVEIL — TwinVEIL: A privacy-preserving framework for 6G Digital Twins using CKKS homomorphic encryption for secure edge-to-cloud anomaly detection.
  8. Jun 15, 2026
    Created PassiveScanner — Scan client URL's with a crawler to look for potential threats and vulnerabilities, rank them based on severity and generate a detailed report with analysis on the inference..
  9. Jun 19, 2026
    Created LarpSuite
  10. Aug 8, 2026
    Created ApexLab-source
  11. Aug 12, 2026
    Created CRISMA
  12. Aug 29, 2026
    Most recent push to dileeme

07 · Compare

github.com/
dileeme · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total56.1
Top-end curve+4.0
Final overall60.1

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.
dileeme · 60.1/100 — Rate My GitHub