01 · Roasts
69% Jupyter, 0% Shipping
Your language breakdown is 69% Jupyter Notebook — meaning most of your GitHub is notebooks that probably end with 'TODO: clean this up.' The remaining 31% is TypeScript landing pages for products that may or may not exist yet.
lol.py Is Your Magnum Opus
You have a repo called lol-repo containing exactly one line: print('lol'). Created and pushed in 3 seconds. No README. No license. Just vibes. This is in your public portfolio alongside a YC demo site.
71 Repos, 33 Total Stars
You've created 71 repos and accumulated 33 stars — that's 0.46 stars per repo. At this rate you'll hit 1 star/repo by 2097. Quality over quantity is a thing.
CI? Never Heard of Her
Zero repos with CI detected across the entire analyzed portfolio. You have TypeScript projects, Next.js deployments, even a test suite in ara-app-review-demo — but not a single GitHub Action to verify any of it runs.
new-repo-test-2 Has Been Live for 8 Months
new-repo-test-2 — literally named 'new-repo-test-2' — is a 2KB placeholder that has sat untouched for 8+ months. The test was: can I create a repo? The answer is yes. The follow-up: apparently not required.
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% weight36F
- Consistency20% weight65C
- Quality20% weight57D
- Depth15% weight50D
- Breadth10% weight55D
- Community10% weight40D
03 · Stats
365-day commit heatmap
309 active days
Language distribution
- Jupyter Notebook69%
- TypeScript24%
- Swift4%
- Python1%
- JavaScript1%
- CSS0%
- Other1%
04 · Numbers
Owned repos
non-fork
62
Commits
last 12 months
1,561
Followers
84
Joined GitHub
Aug 2023
05 · Top repos
adisinghstudent /
coshot.dev
Early-stage SaaS landing page for AI autocomplete tool. TypeScript + Next.js with Vercel deployment, structured layout, but no tests or CI. Limited scope and adoption (1 star, recent June 2025 commits).
adisinghstudent /
brreg
Personal agent skill wrapper for Norwegian Business Registry API; minimal codebase (3 KB), no tests/CI/license, but functional docs and clear README describing feature set.
adisinghstudent /
ara-app-review-demo
Minimal demo project with a single utility function and test suite. Demonstrates Ara for App Review with zero dependencies, clear documentation, and passing tests—but intentionally tiny scope and one-shot deployment.
adisinghstudent /
adisinghstudent
GitHub profile config repo with minimal content (33 KB). Contains a README with the owner's bio and accomplishments but lacks code artifacts, tests, CI, or structured project deliverables. Represents a personal profile page rather than a software project.
adisinghstudent /
yc-demo
YC W26 demo site for Ara agent-builder. Fresh Next.js marketing page with TypeScript; no tests, CI, or real substance beyond a landing page template for a stealth-stage product.
adisinghstudent /
untitled-app
Empty-slate one-shot scaffold: 3KB repo with single commit demonstrating Typer/Rich CLI boilerplate. Zero adoption signals. Works but is a template dump.
adisinghstudent /
Community
Empty community discussion repo with minimal README, no source files, 1 KB total size, single commit in 3-month window. Scaffold-only project with no code contribution.
adisinghstudent /
new-repo-test-2
Empty scaffold repo with minimal README and no source code. Created via assistant with only 1 commit across 8+ months. No tests, CI, license, or typed code present.
adisinghstudent /
lol-repo
Empty scaffold repo with single trivial print statement, no README, tests, CI, license, or documentation. Created and pushed within 3 seconds with 1 commit.
06 · Timeline
- Aug 28, 2023Joined GitHub
- Sep 12, 2023Created adisinghstudent — Config files for my GitHub profile.
- Jul 4, 2025Created coshot.dev — Coshot.dev - AI-powered suggestive autocomplete for computer
- Oct 17, 2025Created new-repo-test-2 — Public repository created via assistant
- Jan 26, 2026Created brreg — npx add-skill adisinghstudent/brreg
- Mar 16, 2026Created Community — Ara Community — Discussions, feature requests, bug reports
- May 31, 2026Created untitled-app
- Jun 1, 2026Created lol-repo
- Jun 4, 2026Created yc-demo — Ara YC W26 demo site
- Jul 30, 2026Created ara-app-review-demo — A tiny, non-production sample project for demonstrating Ara during App Review.
- Jul 30, 2026Most recent push to ara-app-review-demo
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.