01 · Roasts
The Testless Armada
9 repos analyzed, 9 repos with HAS_TESTS=no and HAS_CI=no. That's not a pattern, that's a philosophy. At some point 'quietly building' starts sounding like 'quietly hoping nothing breaks.'
README > Reality
Hybrid-Recomendatiion-system: 17 KB, 4 commits in one day, a README promising Flask APIs and Streamlit apps, and zero actual code files. The README shipped; the code did not.
4 Stars Across 52 Repos
52 public repos, totalStars=4 — two of which live on Doc-Agent alone. The rest of the portfolio is in a stellar silence so deep it bends light.
Dependency Gaslighting
BugX's requirements.txt lists only google_genai and python-dotenv, yet orchestrator.py imports LangChain throughout. The deps file is not just sparse — it's fiction.
HTML 56%
You're building AI agents, LSTM pipelines, and multi-LLM RAG systems — yet HTML is 56% of your language footprint. Those Jupyter notebooks and static files are really living rent-free in your stats.
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
- Impact25% weight56D
- Consistency20% weight65C
- Quality20% weight52D
- Depth15% weight58D
- Breadth10% weight65C
- Community10% weight50D
03 · Stats
365-day commit heatmap
168 active days
Language distribution
- HTML56%
- Python21%
- JavaScript12%
- TypeScript10%
- CSS1%
- SCSS0%
04 · Numbers
Owned repos
non-fork
46
Commits
last 12 months
489
Followers
15
Joined GitHub
Jul 2023
05 · Top repos
ravikrishnaj25 /
ZenMod
AI-powered React code generator with Vite sandbox integration, running 14.8MB TypeScript codebase. Has typed code, docs, structured architecture, but no tests or CI. Early-stage personal project (3 months old, 30 commits).
ravikrishnaj25 /
Automated-ELT-Data-Pipeline-LLM-Powered-Youtube-Video-Insights
Personal portfolio project demonstrating end-to-end data engineering with Airflow, Databricks, dbt, Django, and AWS infrastructure. Non-trivial scope with meaningful docs, but lacks tests, CI, typed code, and production evidence.
ravikrishnaj25 /
Supply-Chain-Inventory-Optimization-using-LSTM
Educational Streamlit app for pharmaceutical supply chain analysis with LSTM forecasting, inventory optimization (EOQ/safety stock), and statistical testing. Well-documented synthetic dataset project built over 7.5 months, untyped Python with no tests or CI.
ravikrishnaj25 /
VisionFit
VisionFit AI is an early-stage body measurement CV system combining MediaPipe pose landmarks + MobileNetV2 CNN regression with FastAPI backend and React frontend. Typed Python, documented README, modular src/ structure, but no tests, CI, or production licensing; ~2.9 KB codebase suggests nascent state.
ravikrishnaj25 /
-BugX
BugX is a LangChain-based agentic CLI tool for code debugging using Google Gemini API. Typed Python with modular tool architecture but missing tests, CI/CD, and lacks sustained contribution depth despite recent activity.
ravikrishnaj25 /
Doc-Agent
Personal Docker-agentic project integrating LangGraph, LlamaIndex, and multiple LLMs with RAG, vector stores, and Prometheus monitoring. No type hints in Python, no tests, no CI, but demonstrates working multi-service architecture.
ravikrishnaj25 /
PlotWise
Early-stage data visualization chatbot using Dash, Gemini, and Cohere APIs. Untyped Python project with README and working demo, but no tests, CI, or visible source code structure in sampling. Experimental scope with documented development challenges.
ravikrishnaj25 /
SalesIntel-Agents
Early-stage AI agent pipeline for competitive sales battle cards, built on Google ADK. Minimal GitHub footprint (0 stars, 15 days old), sparse README, no tests/CI/license, untyped Python with basic project structure and Google Generative AI dependencies.
ravikrishnaj25 /
Hybrid-Recomendatiion-system
One-day-old Jupyter-based skincare recommendation project with README but no code files, tests, CI, or license. Purely experimental scaffold on Kaggle dataset.
06 · Timeline
- Jul 11, 2023Joined GitHub
- Nov 30, 2024Created PlotWise
- Mar 8, 2025Created VisionFit — VisionFit AI is a smart body measurement system
- May 31, 2025Created Doc-Agent — automating docker flow with Docker Agents with multiple LLM's, Vector Stores and Agentic Frameworks with Traces for Monitoring the Llms
- Jul 16, 2025Created Supply-Chain-Inventory-Optimization-using-LSTM
- Jul 16, 2025Created Automated-ELT-Data-Pipeline-LLM-Powered-Youtube-Video-Insights
- Nov 11, 2025Created -BugX — BugX is an intelligent, agentic CLI tool that uses Google’s Gemini API to automatically analyze, debug, and repair Python projects. Inspired by tools like Cursor, GitHub Copilot .
- Jan 12, 2026Created ZenMod — AI Vibe Coding Tool
- Mar 17, 2026Created Hybrid-Recomendatiion-system
- Apr 18, 2026Created SalesIntel-Agents — AI Data Quality Checker
- May 3, 2026Most recent push to SalesIntel-Agents
07 · Compare
08 · Rubric
How this score was produced
Overall = Σ (category × weight) + gentle top-end curve
Tier thresholds
▸ How the pipeline works
- 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.
- 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
- 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.
- 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.
- 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.