01 · Roasts
Test-Free Zone
HAS_TESTS=no across every single one of 9 scored repos. Not one test file anywhere. You're shipping AI stock trackers and data pipelines entirely on vibes and prayer.
Speed Runner of Software
DataVizA5: 49 minutes. DataVizA4: 1 hour. sankey-example: 45 minutes. mizmaa: created and abandoned same day. Your GitHub history reads like a hackathon with no demo day.
0 Stars, 0 Forks, 0 Friends
totalStars=0, totalForks=0, followers=0, totalPRsYear=0, totalIssuesYear=0. soloPct=100. You are coding in a sealed room with the lights off and no one knows you exist.
Profile README Has More Commits Than Your Apps
codyk2 (your profile README) logged 14 commits polishing badges and career summaries. Meanwhile ai-stock-sentiment-tracker shipped with 1 commit 'in 2 seconds.' Priorities noted.
Coming Soon™
Your portfolio README literally says 'coming soon.' You joined GitHub in January 2023 and have 0 public stars to show for it. At what point does 'soon' become a philosophical concept?
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% weight57D
- Depth15% weight35F
- Breadth10% weight65C
- Community10% weight25F
03 · Stats
365-day commit heatmap
40 active days
Language distribution
- TypeScript53%
- HTML21%
- JavaScript9%
- Python7%
- CSS6%
- Lua3%
- Other1%
04 · Numbers
Owned repos
non-fork
12
Commits
last 12 months
34
Followers
0
Joined GitHub
Jan 2023
05 · Top repos
codyk2 /
sleep-and-success
Single-author scrollytelling data visualization in Quarto/Plotly analyzing CMU sleep-GPA dataset. Well-documented design rationale and interactive exploration interface, but nascent repo (9 days old) with minimal adoption or external validation.
codyk2 /
spacex-news
Personal automation project: Python scraper aggregating SpaceX news from 12+ RSS feeds, Twitter/X, and web sources, synthesizes daily with Claude AI, publishes static HTML digest to GitHub Pages via daily GitHub Actions workflow.
codyk2 /
mizmaa
Early-stage TypeScript Next.js demo for VC automation with mock agents, portfolio monitoring, and deal screening UIs. No README, no tests, no CI/license. Created and last pushed same day (Apr 8, 2026). Shows 163 KB structured codebase with component design patterns.
codyk2 /
ai-stock-sentiment-tracker
TypeScript full-stack stock sentiment analyzer with AI-powered news analysis, watchlist management, and price charting. Typed, documented with architectural design files, structured client/server layout, but brand new (created 2026-02-18 with 1 commit in 2 seconds) and lacks tests/CI.
codyk2 /
DataVizA5
Academic assignment visualizing OECD emissions via earnest vs. deceptive chart pair. Single-session work (2 commits in 49 minutes, 202 KB) with working Python code, clear README, and structured pedagogical intent but minimal sustained development or reuse potential.
codyk2 /
codyk2
Personal portfolio README with profile badges and career summary; 38 KB, no source code, tests, CI, or license. Appears to be a profile repo rather than a functional project.
codyk2 /
DataVizA4
A4 assignment project: single-purpose data visualization of US sunshine hours using Node.js canvas. Two files (create_viz.js, server.js), 131 KB, created and completed within one hour. Clean visualization logic but minimal documentation and no tests.
codyk2 /
sankey-example
Tutorial-grade Sankey diagram example in Python and R for data visualization class, with 6 commits over hours and minimal scope. Lacks tests, CI, license, and typed code.
codyk2 /
portfolio
Personal portfolio project with minimal output: 0 stars, 2 commits in 20 minutes, CSS-only, no docs, tests, or CI. Empty scaffold with .gitignore but no substantive code sampled.
06 · Timeline
- Jan 6, 2023Joined GitHub
- Feb 9, 2026Created portfolio
- Feb 18, 2026Created sankey-example
- Feb 18, 2026Created codyk2
- Feb 18, 2026Created ai-stock-sentiment-tracker
- Feb 23, 2026Created DataVizA4 — A4: Visualization Design - Monthly Hours of Sunshine in Major U.S. Cities
- Mar 3, 2026Created DataVizA5
- Mar 31, 2026Created sleep-and-success — Sleep & Success: Interactive Scrollytelling Visualization - Does sleep predict GPA in college freshmen?
- Apr 2, 2026Created spacex-news — SpaceX News
- Apr 8, 2026Created mizmaa — MizMaa Ventures x NemoClaw AI Agents Demo — Deal screening, portfolio monitoring, and due diligence automation
- Apr 18, 2026Most recent push to spacex-news
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.