01 · Roasts
Graveyard of Zero Stars
9 repos, 0 stars total. Not a single person on the internet has clicked ⭐ on anything you've shipped. Even your mom hasn't found your GitHub yet.
Test-Phobic
0 out of 9 repos have tests. You're shipping a stealth interview assistant and a fruit-sharing SaaS on vibes and prayer alone. What could go wrong?
The 7-Hour Carnivorous Plant Expert
LearnCarnivorousPlants: created at 9am, last pushed by 4pm, 3 commits, 28 KB. The lifecycle of a weekend project that didn't survive the weekend.
CI? Never Heard of Her
8 of 9 repos have zero CI. jar-ai is the lone exception, which is impressive — until you realize it also has no README and no tests. Automated nothing, documented nothing.
Joined Yesterday, Already Overambitious
Account is ~9 months old and you've already attempted a Rust voice agent, a FAISS RAG interview assistant, AND a fruit-sharing platform. Bold vision. Zero production deployments. Classic.
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% weight62C
- Consistency20% weight65C
- Quality20% weight62C
- Depth15% weight58D
- Breadth10% weight65C
- Community10% weight25F
03 · Stats
365-day commit heatmap
51 active days
Language distribution
- Jupyter Notebook41%
- Makefile34%
- TypeScript9%
- Rust6%
- Python4%
- JavaScript3%
- Other3%
04 · Numbers
Owned repos
non-fork
10
Commits
last 12 months
310
Followers
1
Joined GitHub
Jul 2024
05 · Top repos
vishc1 /
FruityApp
Next.js fruit-sharing platform with Supabase backend, typed code, structured architecture, and alternate docs. No tests/CI; young repo (2.5 months) with 30 commits representing solid indie project scope but limited production adoption.
vishc1 /
TechBuddy
TypeScript Next.js app for senior-friendly screenshot analysis via Claude/OpenAI vision. Well-documented with README, typed codebase, structured layout, and thoughtful UI (voice output, scam detection, accessible text sizing). No tests/CI and minimal deployment history limit depth.
vishc1 /
jar-ai
Jarvis: an ambitious multi-module macOS voice agent in Rust with egui UI, LLM planning/execution, browser automation, and speech I/O. Well-architected with 172MB codebase but lacks documentation, tests, and is pre-release (0 stars, no external adoption).
vishc1 /
FocusFlip
Early-stage AI-powered focus tool with camera detection & page scoring. Untyped JavaScript, no tests/CI/license. Demonstrates real product thinking (Chrome extension, overlay UX, redirect logic) but lacks shipping maturity.
vishc1 /
Schedule-Helper
Personal schedule-logging app: React + Express.js calendar UI with SQLite backend. Untyped, no tests/CI/docs, minimal scope (~60 KB), 3 commits in 5 days. Works but clearly experimental.
vishc1 /
Question-Assister
Experimental stealth interview assistant with Windows API overlay and dual-channel audio capture. Untyped Python, minimal documentation, no tests/CI. Functional but architectural and design concerns; incomplete RAG/transcription integration.
vishc1 /
Phone-Holder-Sensor-Code
RF interference detection project using AD8317 amplifier and Arduino/ADC hardware integration. Has README explaining cellular ping analysis approach, but minimal code samples provided, no tests/CI, no license, and sparse documentation of implementation details.
vishc1 /
Eventratingapp
Next.js Halloween/Christmas house-rating PWA with TypeScript, Leaflet maps, and Vercel KV storage. Functional but undocumented, unversioned, no tests/CI, and minimal adoption signals.
vishc1 /
LearnCarnivorousPlants
Minimal educational HTML site about carnivorous plants, created and pushed within 7 hours. Single sparse README, no tests, CI, license, or .gitignore. No actual substantive files sampled or available.
06 · Timeline
- Jul 21, 2024Joined GitHub
- Nov 29, 2025Created Eventratingapp
- Jan 20, 2026Created Phone-Holder-Sensor-Code
- Jan 31, 2026Created FruityApp
- Mar 14, 2026Created Question-Assister
- Mar 24, 2026Created jar-ai
- Mar 25, 2026Created FocusFlip
- Mar 30, 2026Created Schedule-Helper
- Apr 10, 2026Created LearnCarnivorousPlants — Website, that teaches about carnivorous plants.
- Apr 16, 2026Created TechBuddy
- Apr 21, 2026Most recent push to jar-ai
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.