01 · Roasts
98% Jupyter, 2% Regret
Your language breakdown is 98% Jupyter Notebook. That's not a tech stack — that's a course syllabus. A .py file is right there, Jordan. One click away.
Zero Followers, Zero Forks, Zero Stars
16 repos, 0 stars, 0 forks, 0 followers. The github.com/jordanjasonclifford page is basically a tree falling in an empty forest — technically it happened, but did it?
The Heatmap Tells the Truth
Your contribution graph is 40 weeks of silence followed by a frantic April sprint. That's not consistency — that's cramming for finals. The real world doesn't have finals week.
NeetCode Did the Commits for You
Your most recent repo (neetcode-submissions) explicitly admits it was 'auto-generated by NeetCode.io GitHub Sync.' Counting auto-synced submissions as your commits is the developer equivalent of listing 'breathing' on your resume.
meme README Machine
nba_machine_learning's README is literally a meme image and one vague sentence. The project is 6 days old and already spiritually abandoned. That's a new record even by student-project standards.
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% weight65C
- Quality20% weight57D
- Depth15% weight58D
- Breadth10% weight30F
- Community10% weight25F
03 · Stats
365-day commit heatmap
58 active days
Language distribution
- Jupyter Notebook98%
- Python1%
- HTML0%
- JavaScript0%
- CSS0%
- PLpgSQL0%
- Other1%
04 · Numbers
Owned repos
non-fork
13
Commits
last 12 months
222
Followers
0
Joined GitHub
Nov 2022
05 · Top repos
jordanjasonclifford /
Multi-Modal-Route-Optimization-with-Hybrid-Travel
REU research project on multi-modal route optimization using ML-based travel time prediction and cost functions to recommend transport modes. Features a live Streamlit demo, 24.7k routes in Seattle dataset, and Random Forest model trained on real-world Google Maps data.
jordanjasonclifford /
nba_data_engineering
Personal NBA analytics project analyzing Devin Booker's career via Python ETL pipeline feeding PostgreSQL warehouse with SQL marts and Power BI dashboard. Structured, documented, 7.2 MB of substantive code with modular data engineering pattern.
jordanjasonclifford /
call_center_agent
Early-stage AI sales agent with live script optimization loop using Claude, edge-tts, and Whisper. Typed Python, structured layout (agent/, web/, scripts/), documented with README + evaluation.md. Limited ecosystem reach but demonstrates non-trivial architecture and ~1000 LOC codebase built in 4-day span (2026-04-06 to
jordanjasonclifford /
ai110-module3show-musicrecommendersimulation-starter
A classroom music recommender system with typed Python code, documented scoring algorithm, test coverage, and thoughtful bias analysis. Small scope (1099 KB), young repo (created April 2026), 11 commits across 2 hours.
jordanjasonclifford /
jordan-clifford-personal
Personal portfolio website built with React + Vite + Tailwind. Showcases 8 projects and 3 internship experiences. Untyped JS, no tests/CI, generic Vite README, but structured multi-component architecture and functioning site deployed with analytics tracking.
jordanjasonclifford /
neetcode-submissions
Auto-generated NeetCode.io problem submission archive with 30 commits over 8 days. Well-commented algorithm solutions in Python (graphs, heaps, DFS, DP) but no tests, CI, or license. Functional as a personal learning portfolio but not a shipping product.
jordanjasonclifford /
nba_machine_learning
Early-stage NBA ML project (6 days old) with vague README and minimal structure. No tests, CI, or license; untyped Python; 0 stars/forks. Personal experimental work dependent on another repo.
jordanjasonclifford /
jordanjasonclifford
A personal portfolio intro repo with a decorated README and no source code. Contains only 27 KB of content across ~10 commits in ~3 weeks, minimal actionable substance, and serves as a GitHub profile card rather than a working project.
jordanjasonclifford /
atlanta-crime-dataset
Class assignment repository with minimal documentation (README states only "Machine Learning class"), no tests/CI, 11MB Jupyter notebooks, 8 commits over ~27 days — experimental coursework project.
06 · Timeline
- Nov 16, 2022Joined GitHub
- Jun 2, 2025Created Multi-Modal-Route-Optimization-with-Hybrid-Travel — Summer Research Project done at UNLV for their Smart Cities 2025 REU Program, Sponsored by the NSF!
- Feb 26, 2026Created atlanta-crime-dataset — Machine Learning class
- Feb 26, 2026Created jordan-clifford-personal — Portfolio Website
- Feb 27, 2026Created nba_data_engineering — An insight look in how an NBA All-Star can impact their team, with this project taking a specific look within Devin Booker
- Mar 31, 2026Created jordanjasonclifford — My own intro section, get to learn more about me!
- Apr 6, 2026Created call_center_agent — An AI Powered (Claude Sonnet 4.6) Call Center Agent, handling the sale of a hypothetical CRM
- Apr 13, 2026Created ai110-module3show-musicrecommendersimulation-starter
- Apr 14, 2026Created nba_machine_learning
- Apr 21, 2026Created neetcode-submissions — My NeetCode.io problem submissions
- Apr 29, 2026Most recent push to neetcode-submissions
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.