01 · Roasts
One-Trick Star Factory
claurst has 9,522 stars and 7,823 forks. Every other repo combined can't crack 100 stars. You're not a portfolio — you're a solar system with one very bright sun and a lot of space debris.
Sprint-and-Ghost Strategist
pokeclaw was born and architecturally documented in 34 minutes flat, bda-sga2 was pushed in 6 minutes, and the-archon is still an empty scaffold. You ship fast and then immediately start the next thing before the paint dries.
Test Allergy
11 out of 12 repos have HAS_TESTS=no. claurst has 12 crates and supports 30+ LLM providers but apparently zero test files. The codebase is typed and beautifully structured — it's just spiritually opposed to assertions.
Automation Ouroboros
You have at least 3 separate repos (MindDump-Preview-Update, awesome-idea-of-the-day-archive, Dynamic-Readme-Images) all doing the same thing: Puppeteer + GitHub Actions cron + screenshot. Each one even links to the previous one as the 'real' version. It's automation all the way down.
90% Solo Act
680 followers, 9.5k stars on claurst, and a soloPct of 90%. The community came to you — you just never went to them. 17 external PRs in a year for someone with this reach is leaving serious collaboration karma on the table.
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% weight81A
- Consistency20% weight72B
- Quality20% weight69C
- Depth15% weight75B
- Breadth10% weight80A
- Community10% weight55D
03 · Stats
365-day commit heatmap
343 active days
Language distribution
- Python38%
- HTML28%
- Rust15%
- Jupyter Notebook8%
- Kotlin4%
- TypeScript4%
- Other3%
04 · Numbers
Owned repos
non-fork
35
Commits
last 12 months
976
Followers
680
Joined GitHub
Jan 2022
05 · Top repos
Kuberwastaken /
claurst
Production-grade Rust terminal coding agent with 9.5k stars, comprehensive multi-provider LLM support, rich TUI, extensive CLI, modular architecture (12 crates), and exhaustive documentation. Active development with recent pushes and well-structured codebase meeting 75+ quality tier criteria.
Kuberwastaken /
Kuberwastaken.github.io
Terminal-styled React portfolio with interactive games, a multi-project showcase, and 30 recent commits. Well-structured React app with 90KB codebase, theme context, and lazy-loaded components, but limited external adoption (1 star).
Kuberwastaken /
awesome-idea-of-the-day-archive
Automated screenshot archival tool using Puppeteer and GitHub Actions to capture daily ideas from ideabrowser.com with organized folder structure and CI/CD pipeline.
Kuberwastaken /
Dynamic-Readme-Images
Template repository for dynamically updating README images via GitHub Actions + Puppeteer. Well-commented code with functional CI workflow, but limited scope and adoption (7 stars). Suitable for personal/portfolio use.
Kuberwastaken /
blog
Terminal-inspired Quartz blog (TypeScript/SCSS/Markdown) with 15 stars, CC-BY-SA license, light/dark modes. Started Jan 2025, 30 recent commits, 13.5MB codebase. Personal project with testing infrastructure but thin adoption.
Kuberwastaken /
nogreeting
Fast-shipped Next.js generator for custom "no greeting" landing pages. Typed, structured, with multilingual support (19 languages) and customizable UI, but no tests/CI and minimal production adoption (3 stars, ~957KB).
Kuberwastaken /
MindDump-Preview-Update
A lightweight screenshot automation tool built in JavaScript using Puppeteer. Runs daily via GitHub Actions to capture blog updates. Functional and shipped, but minimal scope and undocumented codebase.
Kuberwastaken /
HOBOEM
Early-stage Next.js e-commerce prototype with CI/CD deployment pipeline. Minimal adoption (1 star), thin docs, and incomplete product generation logic suggest active experimentation rather than production-ready software.
Kuberwastaken /
pokeclaw
Minimal MCP bridge blueprint with clear environment-driven design. JavaScript ES modules, documented via README + ARCHITECTURE/TOOL_SPEC/LIVENESS markdown files, but no tests, CI, or license. Created and completed within ~34 minutes on 2026-05-06.
Kuberwastaken /
bda-sga2
Student coursework: Spring Boot library manager with working CRUD, bidirectional JPA relationships, and basic test coverage. Type-safe, documented, but minimal real-world scope.
Kuberwastaken /
Kuberwastaken
Personal portfolio/identity repo with interactive DOOM game in README. Minimal code content, no source files sampled, no tests or license. Represents personal branding rather than a shipped product.
Kuberwastaken /
the-archon
Empty or near-empty JavaScript scaffold with no README, docs, tests, CI, or license. Only 1 star, created 2026-04-25, 7 commits in 30 days. No source files fetched indicates minimal substance.
06 · Timeline
- Jan 3, 2022Joined GitHub
- Oct 24, 2024Created Kuberwastaken
- Dec 21, 2024Created Kuberwastaken.github.io — The Best Terminal-Inspired Portfolio Website on The Internet™
- Jan 3, 2025Created blog — ᨒ MindDump - The Best Terminal-Inspired Blog Website on The Internet™
- Feb 19, 2025Created MindDump-Preview-Update — Automatically takes a screenshot to capture updates on my Blog Website - MindDump everyday!
- Feb 19, 2025Created Dynamic-Readme-Images — A Template Repository to get "Dynamically Updating" Pictures in Readme
- Jul 14, 2025Created awesome-idea-of-the-day-archive — Takes a screenshot of ideabrowser.com everyday
- Oct 27, 2025Created nogreeting — Imagine calling someone on the phone, going [GREETING]! then putting them on hold, if you see this link on someone's bio, just [GREETING] will likely get you ghosted
- Jan 9, 2026Created HOBOEM
- Mar 31, 2026Created claurst — Your favorite Terminal Coding Agent, now in Rust
- Apr 25, 2026Created the-archon
- May 2, 2026Created bda-sga2 — Building a Library Manager App from Scratch with Spring Boot
- May 6, 2026Created pokeclaw — An MCP bridge and skill to give poke persistent hardware to run on
- May 7, 2026Most recent push to MindDump-Preview-Update
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.