01 · Roasts
Commit confetti cannon
837 yearly commits and 198 multi-repo volume say you ship relentlessly; 17 total stars say the audience has not found the venue yet.
CI knows your name
WebcamCCTV, LLMCookieBridge, prism-insight-light, and autonomous-maintainer brought real tests and CI; several smaller repos still treat verification as optional DLC.
Security jump scare
FakeNewsDetector hard-codes Naver credentials, while the rest of the portfolio is busy demonstrating that you clearly know better.
Product multiverse
Trading runtime, CCTV desktop app, 61-provider bridge, hardware game, and web tools: this is a portfolio, not a single-repo situationship.
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% weight68C
- Consistency20% weight65C
- Quality20% weight75B
- Depth15% weight58D
- Breadth10% weight65C
- Community10% weight30F
03 · Stats
365-day commit heatmap
117 active days
Language distribution
- Python65%
- TypeScript21%
- Shell5%
- JavaScript3%
- HTML2%
- CSS2%
- Other2%
04 · Numbers
Owned repos
non-fork
17
Commits
last 12 months
837
Followers
1
Joined GitHub
Sep 2020
05 · Top repos
tkgo11 /
prism-insight-light
A substantial Python trading runtime integrating GCP Pub/Sub, KIS KR/US execution, multi-account ledgers, strategy modules, stop-loss monitoring, and a guarded FastAPI WebUI, with strong testing and CI but limited visible adoption.
tkgo11 /
WebcamCCTV
A carefully engineered local-first Python desktop CCTV application with separate GUI/service processes, robust recording and retention workflows, tests, CI, and cross-platform packaging, but only 1 star and no stated external adoption.
tkgo11 /
LLMCookieBridge
A documented async Python library exposing 61 AI/web providers through a shared streaming and session-refresh API, with strong tests and CI but limited demonstrated adoption at 4 stars.
tkgo11 /
codex-autonomous-maintainer
A documented, cross-platform Codex skill package with Bash and PowerShell installers, structural validators, checksum/release checks, and extensive installer tests; adoption remains low at 2 stars.
tkgo11 /
FakeNewsDetector
A documented MIT-licensed Python/Chrome extension prototype with Naver and SNU FactCheck integrations, but only 1 star, no tests or CI, hard-coded API credentials, and fragile heuristic scoring limit readiness and adoption.
tkgo11 /
IfGPT
A documented Python rule-based chatbot with a 2,400-record JSONL corpus, dedicated validator, strict CI checks, and substantial defensive error handling, but no visible adoption or external product evidence.
tkgo11 /
moclaw-trial-generator
A documented single-file Python automation tool for disposable-email MoClaw trial registration, including OTP polling, Camoufox browser control, bulk workers, and JSON credential output, but no tests, CI, license, or typed language.
tkgo11 /
MBTI_test
A documented Korean-language vanilla JavaScript MBTI web test with 40 questions, responsive styling, scoring, result descriptions, preference bars, and restart/share UI, but no tests or CI.
tkgo11 /
PyPhy_RoundGame
A small MicroPython hardware game in main.py, integrating BLE, SSD1306 OLED output, and 12 NeoPixels with a simple score-and-timing loop.
tkgo11 /
tkgo11
A small GitHub profile README repository backed by a single data.json configuration; it has no demonstrated adoption, typed implementation, tests, CI, license, or substantial product scope.
tkgo11 /
chungdahm-Skill-Practice-hacking
A small, discontinued Chrome extension that extracts answer text from a Chungdahm iframe; it has a README and manifest but minimal structure, no tests or CI, and a risky upload helper.
tkgo11 /
wrtn-system-prompt
A small, documented Korean-language system-prompt repository containing a single README artifact, with minimal adoption and no implementation, tests, CI, licensing, or demonstrated sustained development.
06 · Timeline
- Sep 24, 2020Joined GitHub
- Feb 19, 2023Created chungdahm-Skill-Practice-hacking — 청담 Skill Practice의 답을 가져오는 확장프로그램 입니다.
- Aug 7, 2024Created PyPhy_RoundGame — 파이파이 키트에서 빙글빙글게임 구현
- Aug 31, 2024Created FakeNewsDetector
- Aug 31, 2024Created tkgo11
- Apr 7, 2025Created MBTI_test — MBTI 성격 유형 테스트
- May 11, 2025Created wrtn-system-prompt — 뤼튼의 시스템 프롬프트 입니다
- Dec 1, 2025Created prism-insight-light — AI-based stock analysis and trading system. Now only with GCP Pub/Sub trading function.
- Apr 18, 2026Created LLMCookieBridge — Unified async Python access to major AI web apps using browser-session cookies instead of official API keys.
- May 9, 2026Created moclaw-trial-generator — Automates MoClaw free-trial registration using disposable emails. Supports single and bulk account generation.
- Jul 2, 2026Created codex-autonomous-maintainer — Repository-wide Codex skills that discover, implement, verify, and prepare comprehensive improvements with a mandatory pre-PR approval gate.
- Aug 2, 2026Created WebcamCCTV — A local-first desktop webcam CCTV system.
- Aug 19, 2026Created IfGPT
- Sep 23, 2026Most recent push to chungdahm-Skill-Practice-hacking
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.