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

#291 — Top 75.7%

Tosin-A

Tosin Adedokun

D

README enthusiast

Overall

0.0

/ 100

01 · Roasts

Sprint Merchant

6 out of 7 repos were created within a 4-month window in 2026, several within single sessions (Tradingalgz: 2 commits in 37 minutes). You're not building software — you're speedrunning the GitHub commit graph.

Architect Without Tests

Coresense-Backend- has an ARCHITECTURE.md, a STATUS.md, a design.md, AND a docs/ folder — but only one repo with actual tests across the whole profile. You document the cathedral; you just don't verify it holds up.

The Truncation Graveyard

Tradingalgz has backtest.py, live_engine.py, and web/app.py all cut off mid-function. That's not a trading system, that's a proof-of-concept that ran out of RAM mid-paste.

1 Star, 6 READMEs

Total stars across 12 public repos: 1. You've written more documentation explaining what these projects will do than commits actually making them do it.

Ghost Town Heatmap

49 out of 52 weeks on your public heatmap are completely dark. privateWorkLikely=true saves your Consistency score, but the public face of this account looks like it only woke up in April 2026.

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
    60C
  • Quality
    20% weight
    57D
  • Depth
    15% weight
    55D
  • Breadth
    10% weight
    65C
  • Community
    10% weight
    25F

03 · Stats

90-day commit heatmap (public events only)

7 active days

Less
More

Language distribution

4 langs
  • Python40%
  • TypeScript30%
  • JavaScript20%
  • CSS10%

04 · Numbers

Owned repos

non-fork

12

Commits

last 12 months

113

Followers

1

Joined GitHub

Jul 2022

05 · Top repos

Tosin-A /

Coresense-Backend-

50/100

FastAPI personal AI coach backend with Supabase integration, multi-router architecture, health insights engine, and message limits. Typed Python with structured modular design, comprehensive docs (README + ARCHITECTURE.md + STATUS.md + design.md), and tests present.

I40Q60D50
READMETests
Python02mo ago

Tosin-A /

portfolio-website

42/100

Personal portfolio website showcasing multiple shipped projects (Coresense, CloutAI, Calitrack). Typed TypeScript + structured src/, HAS_CI with quality checks, but lacks tests and is young (created 2026-04-07, 10 commits in ~10 days).

I25Q60D35
READMECITyped
TypeScript01mo ago

Tosin-A /

Cora-Lockin

42/100

TypeScript AI coaching platform with React Native frontend and FastAPI backend. Well-documented with design artifacts and structured architecture, but no CI, no license, 0 stars, and no source files sampled to verify implementation quality.

I25Q50D50
READMETestsTyped
TypeScript02mo ago

Tosin-A /

coresense-landing

38/100

A React 19 landing page for CoreSense AI health app with clean component structure, responsive design, and GitHub Pages CI/CD. Zero stars/forks suggests early-stage project; untyped JavaScript and no tests limit quality despite solid documentation and working tooling.

I25Q50D35
READMECI
JavaScript02mo ago

Tosin-A /

Typist

37/100

Early-stage typing practice desktop app with gamified curriculum, adaptive difficulty, and cloud leaderboard support. Unfinished onboarding flow and missing key backend methods limit current usability despite solid architecture and CI/CD setup.

I25Q50D35
READMECI
JavaScript01mo ago

Tosin-A /

rag-hybrid

28/100

Educational hybrid RAG prototype combining dense (Chroma) + sparse (BM25) retrieval with RRF fusion and Ollama LLM integration. Well-documented with typed Python code but minimal project history (3 commits, <1 hour old).

I15Q50D20
README
Python01mo ago

Tosin-A /

Tradingalgz

20/100

Incomplete ML + ICT futures trading system (NQ/ES) combining rule-based and deep learning; typed Python with README but no tests/CI/license, truncated files, 0 adoption, single-session commit. Experimental dump.

I15Q40D5
README
Python01mo ago

06 · Timeline

  1. Jul 12, 2022
    Joined GitHub
  2. Dec 10, 2025
    Created coresense-landing — CoreSense landing page - AI health coach app
  3. Jan 6, 2026
    Created Cora-Lockin
  4. Jan 6, 2026
    Created Coresense-Backend-
  5. Apr 7, 2026
    Created portfolio-website — Personal portfolio website (Vite, React, Tailwind)
  6. Apr 8, 2026
    Created Tradingalgz
  7. Apr 15, 2026
    Created rag-hybrid — Local hybrid RAG: dense (ChromaDB + sentence-transformers) + sparse (BM25) retrieval fused with Reciprocal Rank Fusion, answered by Ollama mistral
  8. Apr 16, 2026
    Created Typist — Adaptive typing practice app — electric blue, per-key error tracking, auto-adaptive sessions
  9. Apr 21, 2026
    Most recent push to Typist

07 · Compare

github.com/
Tosin-A · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total54.6
Top-end curve+3.6
Final overall58.3

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.
Tosin-A · 58.3/100 — Rate My GitHub