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

#127 — Top 89.4%

chemicoholic21

Taniya Souza

C

Getting there

Overall

0.0

/ 100

01 · Roasts

The 48-Hour Graveyard

RAG-AI-assistant and Streaming-Video-Platform were born and abandoned within a single day. Two repos, two commits each, both scored under 30. At this rate your GitHub is less a portfolio and more a startup cemetery.

Test? Never Heard of Her

Out of 10 repos, exactly one has real tests — and even those are placeholder comments saying 'Will be fully implemented in Phase 3.' Phase 3 has never arrived in recorded history.

95% Python, 0% pytest

Python is 95% of your codebase by bytes. You clearly love the language. You just refuse to write a single passing test in it. That's a special kind of commitment to living dangerously.

Hackathon Hero, CI Zero

WardWatch won a hackathon with Elasticsearch + AWS Bedrock built in 4 hours. Genuinely impressive. It also has no CI, no tests, and no license. Civic tech deserves better than cowboy deployments.

Burst Mode Developer

Your heatmap is a horror movie: 30 consecutive weeks of near-silence, then a frantic daily burst in the last 5 weeks. The year doesn't have a commit history — it has a plot twist.

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
    62C
  • Consistency
    20% weight
    65C
  • Quality
    20% weight
    65C
  • Depth
    15% weight
    58D
  • Breadth
    10% weight
    55D
  • Community
    10% weight
    55D

03 · Stats

365-day commit heatmap

75 active days

Less
More

Language distribution

7 langs
  • Python95%
  • C2%
  • Cython1%
  • TypeScript1%
  • JavaScript0%
  • C++0%
  • Other1%

04 · Numbers

Owned repos

non-fork

57

Commits

last 12 months

368

Followers

39

Joined GitHub

Jan 2022

05 · Top repos

chemicoholic21 /

Git-Pull-Talent

52/100

Functional Next.js tool for GitHub contributor impact scoring with typed backend, polished UI, multi-tier caching (Redis + Postgres), and public deployment. 20 stars, active development, no tests/CI, complete feature set with leaderboards and user profiles.

I45Q68D42
READMETyped
TypeScript208d ago

chemicoholic21 /

github-data-pipeline

43/100

A TypeScript headless pipeline for discovering GitHub developers, scoring contributions (stars × userPRs/totalPRs), and storing ranked profiles in Postgres. Typed, documented, structured with scoring logic and multi-stage architecture, but experimental scope (0 stars) and early-stage development limit impact.

I25Q60D45
READMETyped
TypeScript0this week

chemicoholic21 /

Portfolio-website

43/100

Personal portfolio site built with Next.js + TypeScript, featuring GSAP animations and custom React components. Typed language, structured layout, README present; lacks tests/CI/license but demonstrates solid foundational craftsmanship.

I25Q60D45
READMETyped
TypeScript01mo ago

chemicoholic21 /

WardWatch

40/100

Hackathon-winning civic observability platform for Bengaluru using Elasticsearch, AWS Bedrock, and TypeScript. Detects unresponsive gov offices, analyzes scam messages, traces complaint escalations. Built solo in ~4 hours with structured backend APIs but thin frontend presence and no tests/CI.

I25Q60D35
READMETyped
TypeScript0this week

chemicoholic21 /

PRISM

38/100

Early-stage TypeScript/Python full-stack app (17 MB) for detecting PR intent drift using local Gemma inference. Typed, documented, and architecturally structured, but pre-launch with minimal adoption signals.

I25Q50D35
READMETyped
TypeScript118d ago

chemicoholic21 /

T-Rex

38/100

Console-based Chrome T-Rex game clone in C++ with Python variant. Minimal scope (48 KB) with jumping, scoring, and rendering. README present with build/play instructions. No tests, no license, no gitignore despite CI setup and 3-year development window (2023–2026).

I25Q40D50
READMECI
C++01mo ago

chemicoholic21 /

Travel-Planner

35/100

Personal Flask travel planner with AI itinerary generation and weather integration. Typed language missing, no tests/CI, but README present, working implementation with user auth and basic structure.

I25Q45D35
README
HTML02mo ago

chemicoholic21 /

RAG-AI-assisstant

28/100

Early-stage RAG assistant with well-documented architecture and thoughtful security design, but unproven and experimental. Fresh repo (48 hours old, 2 commits) with incomplete test suite and no CI pipeline. Promising craft in ingestion/retrieval logic, but thin execution overall.

I15Q45D20
READMETests
Python01mo ago

chemicoholic21 /

Streaming-Video-Platform

15/100

Very early-stage video streaming platform (1 day old, 2 of 30 commits fetched) with minimal documentation, no tests visible in samples, no CI/license, CSS primary language, and zero community adoption.

I5Q25D20
READMETests
CSS01mo ago

chemicoholic21 /

chemicoholic21

7/100

Personal portfolio README with no actual code repository—just a CV/resume listing tech skills and hackathon wins. No source files, no project artifacts, no meaningful codebase.

I5Q10D5
README
Unknown011d ago

06 · Timeline

  1. Jan 6, 2022
    Joined GitHub
  2. Feb 19, 2023
    Created T-Rex — Chrome t-rex game in c++
  3. Sep 26, 2023
    Created chemicoholic21
  4. Jul 14, 2024
    Created Travel-Planner
  5. Jul 17, 2025
    Created Portfolio-website
  6. Mar 6, 2026
    Created Git-Pull-Talent — A public web tool that analyzes a GitHub user’s open-source contributions and computes meaningful impact scores based on repository popularity and pull-request activity.
  7. Mar 31, 2026
    Created github-data-pipeline — A headless data pipeline that ingests, caches, and analyzes GitHub data, transforming it into structured insights stored in Postgres and Redis
  8. Apr 14, 2026
    Created Streaming-Video-Platform — Full-stack video upload, processing, sensitivity analysis, and streaming platform with real-time progress tracking.
  9. Apr 28, 2026
    Created RAG-AI-assisstant — Domain-specific AI assistant built using a custom RAG pipeline that delivers accurate, context-grounded responses while enforcing strict domain boundaries and defending against pro
  10. May 9, 2026
    Created WardWatch — Civic Navigator (featured OpenClaw) - OpenClaw, Bedrock AgentCore EC2, Elasticsearch, Open Crawler, Agent Builder, MCP
  11. May 16, 2026
    Created PRISM — Pull Request Intelligence & Security Machine
  12. May 29, 2026
    Most recent push to WardWatch

07 · Compare

github.com/
chemicoholic21 · 6dmedian coder

08 · Rubric

How this score was produced

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

CategoryWeightScoreContrib.
Raw total61.2
Top-end curve+5.1
Final overall66.3

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.
chemicoholic21 · 66.3/100 — Rate My GitHub