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

#428 — Top 64.2%

RockingAayush

Aayush Rastogi

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

60% Jupyter, 0% Tests

Your language split is 60% Jupyter Notebook yet you've written zero tests across every single repo. Data science without reproducibility isn't science — it's a very confident guess.

One Commit Wonder Weeks

Your heatmap is a dot-to-dot puzzle: 71 commits across the whole year, with stretches of 5–7 consecutive empty weeks. The heatmap looks like a sparse Morse code transmission.

The CI Desert

5 repos scored, 5 repos with HAS_CI=no. Not a single workflow file, not a single badge. You built a full pipelined RISC-V processor but haven't automated so much as a lint check.

Reconfigurable Logic Unit (Empty Edition)

You pushed a repo called Reconfigurable-Logic-Unit, created and abandoned it on the same day, and left it with 20 KB of mystery. It scored a 5. That's not reconfigurable — that's a placeholder with delusions of grandeur.

1 PR All Year

totalPRsYear = 1, totalIssuesYear = 0. You built a pipelined processor from scratch but haven't opened a single issue on anyone else's code. The open-source ecosystem doesn't know you exist yet.

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
    40D
  • Consistency
    20% weight
    55D
  • Quality
    20% weight
    57D
  • Depth
    15% weight
    50D
  • Breadth
    10% weight
    65C
  • Community
    10% weight
    40D

03 · Stats

365-day commit heatmap

38 active days

Less
More

Language distribution

6 langs
  • Jupyter Notebook60%
  • TypeScript16%
  • HTML8%
  • Python8%
  • Verilog5%
  • C++3%

04 · Numbers

Owned repos

non-fork

19

Commits

last 12 months

71

Followers

11

Joined GitHub

May 2021

05 · Top repos

RockingAayush /

Pipelined-RISCV

50/100

Complete 5-stage pipelined RISC-V RV32I processor in Verilog with hazard handling, forwarding, and 813 KB codebase. Well-structured educational project with README, testbench, and FPGA support, but limited external adoption.

I40Q60D50
README
Verilog81mo ago

RockingAayush /

Neural-network-Cpp

38/100

Educational neural network implementation in C++ approximating sine function with custom matrix ops and backpropagation. README documents learning outcomes, typed code with structured layout, Python visualizer includes comprehensive metrics, but no tests, CI, or license.

I20Q50D45
README
Python31mo ago

RockingAayush /

Single-Cycle-Processor-RISCV

33/100

Educational single-cycle RISC-V processor in Verilog supporting all 37 RV32I instructions. Well-documented with block diagrams and demo programs (bubble sort), clean modular architecture, and FPGA deployment path. However, no tests, CI, or license; created 2 days ago with minimal commit history.

I25Q50D20
README
Verilog122mo ago

RockingAayush /

OS-Assignments

20/100

Student assignment repo with 4 basic C OS programming exercises (fork, pipes, signals) completed in ~3 days; no README, no tests, minimal documentation; typical one-off coursework submission.

I15Q25D20
C04mo ago

RockingAayush /

Reconfigurable-Logic-Unit

5/100

Empty scaffold: 20KB repo with 0 stars, no files sampled, created and pushed same day, lacks README, tests, CI, and documentation. Unsubstantiated claim of hardware reconfiguration capability.

I5Q10D5
HTML01mo ago

06 · Timeline

  1. May 23, 2021
    Joined GitHub
  2. May 23, 2025
    Created Neural-network-Cpp — A neural network design made from scratch in C++.
  3. Jan 31, 2026
    Created OS-Assignments
  4. Mar 7, 2026
    Created Single-Cycle-Processor-RISCV — This is a simple implementation of the RISC V processor consisting of a single cycle core. It supports all the 37 RV32I Base Integer instructions compliant to the core instruction
  5. Mar 20, 2026
    Created Pipelined-RISCV — This is a simple pipelined implementation of the RISC V processor. It supports all the 37 RV32I Base Integer instructions compliant to the core instruction formats. It also handles
  6. Apr 5, 2026
    Created Reconfigurable-Logic-Unit — This is a dataflow graph execution unit that can be combined with a processor to reconfigure hardware on the fly using memory. It also includes a webapp that lets you generate the
  7. Apr 29, 2026
    Most recent push to Neural-network-Cpp

07 · Compare

github.com/
RockingAayush · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total50.4
Top-end curve+2.7
Final overall53.1

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.
RockingAayush · 53.1/100 — Rate My GitHub