01 · Roasts
CI/CD Who?
8 repos analyzed, 0 CI pipelines. You have property-based money tests and JWT auth logic but not a single GitHub Actions workflow. The robots can't greenlight your PRs if you never invited them.
License? Never Heard of Her
taxform_automation has 2 stars — your most "popular" repo — and still no license. Congratulations, those 2 people technically can't use it legally.
2,359 Commits, 2 Stars
You shipped a financial ledger, a prediction market, a tax extraction pipeline, and a chapter website in under a year. The GitHub star counter reads 2. The market has not discovered you yet.
Profile README Energy
Your AndresL230 profile repo clocks a 116 KB README with 30 commits over 13 months. That's more sustained maintenance than some of your actual codebases.
CLAUDE.md Maximalist
ARCHITECTURE.md, STATUS.md, design.md, CLAUDE.md — you document your projects like a senior engineer but ship without tests or CI like a hackathon participant. Pick a lane.
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% weight80A
- Quality20% weight72B
- Depth15% weight65C
- Breadth10% weight72B
- Community10% weight50D
03 · Stats
365-day commit heatmap
224 active days
Language distribution
- TypeScript50%
- Java17%
- Astro6%
- Python6%
- CSS4%
- Lean4%
- Other13%
04 · Numbers
Owned repos
non-fork
19
Commits
last 12 months
2,359
Followers
20
Joined GitHub
Nov 2024
05 · Top repos
AndresL230 /
andresl.dev
Personal portfolio site showcasing 5 notable hackathon projects (Recost, Canopy, Calyx, Sapling, Eyrie) built with React, TypeScript, Tailwind CSS, and Vite. Well-structured, fully typed, and comprehensively documented with CLAUDE.md design guide.
AndresL230 /
taxform_automation
TypeScript tax form extraction pipeline: classifies W-2/1099 documents, extracts fields via Gemini with confidence scores and bounding boxes, presents results in a React review UI with export to JSON/CSV.
AndresL230 /
sofi-it
Single-week SPA demo showcasing financial decision engine for purchase classification; typed React/TypeScript, Cloudflare Worker backend, structured Zustand state. Incomplete—new repo (1 day old), zero stars/forks, but well-architected personal portfolio project.
AndresL230 /
tally
TypeScript receipt-scanning debt ledger for two people on Cloudflare Workers. Fully typed, documented (README + ARCHITECTURE.md + STATUS.md), tested with Vitest, shipped with migrations and production-ready auth via Cloudflare Access.
AndresL230 /
bu-shpe
Editorial Astro 5 static site for Boston University's SHPE chapter; TypeScript strict, Tailwind v4, content-driven JSON architecture. Deployed to Cloudflare; well-documented project with clear conventions but no tests or license.
AndresL230 /
overvalued
Hackathon booth game: TypeScript + Next.js + Supabase prediction market on résumé legitimacy. Working demo with structured codebase, typed contracts, and thoughtful architecture (O(1) pricing, lazy resolution, bot market-making). No tests, no CI, no license, but substantial documentation and clear multi-week craftsmans
AndresL230 /
neetcode-submissions
Tutorial/study repo: NeetCode.io problem submissions auto-synced from an external platform. 5KB of content, 5 commits over ~2.5 months, no tests/CI/types. Acts as a personal portfolio checkpoint rather than a shipped project.
AndresL230 /
AndresL230
Personal portfolio README of a CS student at Boston University. No source code files present; repo is a profile/resume document only, not a shipping software project.
06 · Timeline
- Nov 30, 2024Joined GitHub
- Jul 25, 2025Created AndresL230
- Feb 21, 2026Created andresl.dev
- May 21, 2026Created neetcode-submissions — My NeetCode.io problem submissions
- May 21, 2026Created bu-shpe
- Jun 23, 2026Created taxform_automation
- Jul 18, 2026Created overvalued
- Aug 11, 2026Created tally
- Aug 25, 2026Created sofi-it
- Aug 26, 2026Most recent push to sofi-it
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.