01 · Roasts
The Graveyard Gardener
Half your repos are single-week sprints that never got a second look — gallery (2 commits, 1 day), junction (5 commits, 2 days), stridelytics (7 commits, 7 days). You plant seeds, forget to water them, and move on.
README? Never Heard of Her
7 of your 10 scored repos are missing a README. forklift, gallery, junction, stridelytics — none of them can explain what they are to anyone who stumbles in, including future you.
1 Star, 1 Fork, 1 Follower
Your entire public GitHub presence has accumulated exactly 1 star, 1 fork, and 1 follower. That 1 follower might be a bot. The 1 star might be self-starred. The math isn't mathing.
CI Is a Myth
Out of 10 repos, exactly one has CI (limbo). You're shipping TypeScript Next.js apps and Electron desktop tools with zero automated testing pipelines. Every merge is a prayer.
Jupyter Notebook Supremacist
52% of your codebase by bytes is Jupyter Notebooks, yet your domainGuess is 'ml' and none of your scored projects are ML tools. That's a lot of homework that never shipped.
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% weight30F
- Consistency20% weight60C
- Quality20% weight57D
- Depth15% weight55D
- Breadth10% weight65C
- Community10% weight25F
03 · Stats
365-day commit heatmap
106 active days
Language distribution
- Jupyter Notebook52%
- TypeScript24%
- JavaScript8%
- HTML8%
- Python5%
- CSS4%
04 · Numbers
Owned repos
non-fork
21
Commits
last 12 months
179
Followers
1
Joined GitHub
Sep 2021
05 · Top repos
jaxsonsprinkles /
limbo
Early-stage Electron + React tray app for ephemeral file management. TypeScript, structured, has CI, but minimal adoption (1 star, created 3 days ago). Solid fundamentals—clear IPC architecture, responsive UI with countdown rings—but unproven in the wild.
jaxsonsprinkles /
cfa-notifications
TypeScript Next.js notification system for Chick-Fil-A club built in 6 days. Features member/event management, cron-based email reminders, Resend integration, and Supabase backend. No tests or CI; minimal documentation beyond README.
jaxsonsprinkles /
honyaku
Early-stage Electron/React/Python desktop app for Japanese transcription with real-time WebSocket streaming. TypeScript frontend, 3337 KB codebase, functional README, working test present but no CI automation.
jaxsonsprinkles /
forklift
Early-stage AI PR automation tool with Textual UI, Python, GitHub/Claude integration. TUI framework chosen but minimal testing, no CI, no license, untyped Python. Clear proof-of-concept but lacks foundational quality infrastructure.
jaxsonsprinkles /
jaxson-duke-fund
Empty scaffold with no README, tests, CI, or license. 18.7 MB HTML project with 8 commits across ~5 weeks shows minimal development velocity and no shipping substance.
jaxsonsprinkles /
jaxsonsprinkles.dev
Personal website repo with 0 stars, no README, no tests/CI, untyped HTML, 5 commits in 6 days. Minimal documentation and no discernible public adoption or reusable patterns.
jaxsonsprinkles /
stridelytics
Minimal experimental repo: 9 KB, 7 commits over 7 days, no README, no tests, no CI, no docs. Python code with no type hints. Barely scaffolded.
jaxsonsprinkles /
junction
Bare Windows app launcher script with no documentation, tests, CI, or type hints. 2KB codebase, 5 commits over 2 days. Experimental personal project with minimal structure.
jaxsonsprinkles /
gallery
Early-stage gallery CLI project with minimal scope: 3 KB, 2 commits in 1 day, no documentation, tests, CI, or license. Experimental code with unfinished implementations and no clear deliverable.
jaxsonsprinkles /
jaxsonsprinkles
Personal README-only portfolio page with no code content, 10KB total size, last active 6 months ago. Links to other projects but this repo itself is empty scaffolding.
06 · Timeline
- Sep 19, 2021Joined GitHub
- Nov 18, 2025Created cfa-notifications — Helping club leaders manage notification emails
- Nov 24, 2025Created jaxsonsprinkles
- Feb 3, 2026Created junction
- Feb 21, 2026Created honyaku — Real-time Japanese translation and transcription desktop app
- Mar 13, 2026Created jaxson-duke-fund
- Mar 29, 2026Created stridelytics
- Apr 8, 2026Created forklift
- Apr 9, 2026Created jaxsonsprinkles.dev — Personal website
- Apr 17, 2026Created gallery
- Apr 22, 2026Created limbo — Download it. Use it. Gone.
- Apr 25, 2026Most recent push to limbo
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.