01 · Roasts
Zero-star startup
Ten analyzed repos, 0 total stars, and 0 forks: the portfolio is shipping into the void.
CI witness protection
zero-trust-auditor has 5 tests, but CI is absent across every scored repository.
Burst-mode builder
shopping-store shipped in roughly one day, while several repos were created and pushed within minutes.
Prototype multiverse
The AI interview simulator has Groq, AssemblyAI, WebRTC, OpenCV, SQLite, and PDFs—then skips tests and a license.
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% weight48D
- Consistency20% weight55D
- Quality20% weight55D
- Depth15% weight35F
- Breadth10% weight55D
- Community10% weight25F
03 · Stats
365-day commit heatmap
12 active days
Language distribution
- Python67%
- TypeScript18%
- JavaScript14%
- CSS1%
- PowerShell0%
04 · Numbers
Owned repos
non-fork
10
Commits
last 12 months
31
Followers
0
Joined GitHub
Dec 2024
05 · Top repos
aliraza0908 /
shopping-store
Éclat is a typed, documented Next.js perfume-store frontend with cart, checkout, Prisma schema, auth, and admin product/order APIs, but it has no visible adoption and remains a very recent, largely mock/demo deployment.
aliraza0908 /
ai-interview-simulator-online-
A documented Streamlit interview simulator with CV parsing, Groq question/evaluation flows, SQLite accounts/history, audio transcription, webcam capture, confidence metrics, and PDF reporting, but no tests, CI, license, or demonstrated adoption.
aliraza0908 /
zero-trust-auditor
A documented, test-backed Python security auditing prototype with five analysis agents, AST reachability mapping, LLM criticism, and PDF/dashboard outputs, but no visible adoption and only a short initial shipping burst.
aliraza0908 /
ai-youtube-automation-bot
A small, documented Python automation prototype with a single monolithic pipeline for AI story generation, TTS, video rendering, and YouTube upload, but no demonstrated adoption, tests, CI, or release hardening.
aliraza0908 /
-ali-portfolio
A polished, documented Next.js portfolio with animated responsive sections, data-driven project content, and accessibility-minded motion handling, but it is a one-commit personal showcase with no tests, CI, license, or demonstrated adoption.
aliraza0908 /
web-site
A newly created, typed Next.js scaffold with a Prisma commerce schema, but the visible app remains the default Create Next App screen and shows no adoption or sustained development.
aliraza0908 /
AI-Interview-Simulator
A documented Streamlit interview simulator with authentication, SQLite interview history, webcam/speech workflow, and Gemini evaluation, but currently shows no adoption, tests, CI, license, or sustained repository history.
aliraza0908 /
aliraza0908
Profile README for an AI/LLM engineer, with no fetched source files, tests, CI, license, or evidence of repository-level implementation or adoption.
aliraza0908 /
repo-health-onboarding-agent
A newly created MIT-licensed scaffold with a minimal README, no fetched implementation files, and only one sampled commit; it shows little evidence of adoption, production use, or sustained engineering.
aliraza0908 /
WiFi-Attendance-System-Cisco
A one-shot Cisco Packet Tracer course-project repository with no fetched source files, documentation, tests, CI, license, or observable implementation artifacts.
06 · Timeline
- Dec 22, 2024Joined GitHub
- Jun 22, 2026Created ai-youtube-automation-bot — Fully automated YouTube story channel bot — AI story generation (Groq/Llama), neural voiceover (Edge TTS), AI thumbnails (Stable Diffusion XL), auto-upload via YouTube Data API
- Jun 29, 2026Created AI-Interview-Simulator — AI-powered mock interview simulator with webcam recording, speech analysis, and automated feedback. Built with Streamlit, AssemblyAI, and Grok.
- Jun 29, 2026Created WiFi-Attendance-System-Cisco — A WiFi-based automated attendance system network designed in Cisco Packet Tracer. Computer Networks course project.
- Jul 16, 2026Created ai-interview-simulator-online- — AI-powered mock interview simulator — parses uploaded CV to generate personalized interview questions, with webcam recording and real-time speech analysis for automated feedback.
- Jul 17, 2026Created -ali-portfolio
- Jul 19, 2026Created web-site
- Jul 19, 2026Created shopping-store
- Aug 29, 2026Created repo-health-onboarding-agent — Agentic Repo Health & Onboarding Assistant - scaffold and initial implementation
- Aug 31, 2026Created zero-trust-auditor — Multi-agent AI security auditing platform — 5 collaborating agents (static analysis, network tracing, DB inspection, architecture mapping, LLM critic) map findings to CWE/OWASP wit
- Sep 15, 2026Created aliraza0908
- Sep 15, 2026Most recent push to ai-interview-simulator-online-
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.