01 · Roasts
README-rich, test-poor
All seven reviewed repositories have READMEs; none has a test suite. Documentation is doing the entire QA department's job.
The invisible launch
weather-app has a live demo, but the portfolio still totals 0 stars and 0 forks across seven repositories.
Workflow tourist
skills-introduction-to-github brings CI and an MIT license, while the actual apps mostly arrive without either.
Planner has a pulse
planner-financeiro accounts for 15 of the recent sampled commits; it is the clearest sign this portfolio is still being actively built.
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% weight36F
- Depth15% weight50D
- Breadth10% weight55D
- Community10% weight25F
03 · Stats
365-day commit heatmap
23 active days
Language distribution
- JavaScript32%
- CSS30%
- HTML30%
- Python8%
04 · Numbers
Owned repos
non-fork
7
Commits
last 12 months
40
Followers
1
Joined GitHub
Oct 2024
05 · Top repos
isadorara /
planner-financeiro
Documented Vite finance dashboard with CSV/manual expense entry, totals, category visualization, and table rendering; useful as a personal project but currently has no adoption signals, tests, CI, or typed code.
isadorara /
weather-app
A small, documented browser weather app with a live GitHub Pages demo and OpenWeather API integration; it has clear UI behavior but remains a tutorial-style JavaScript project without tests, CI, or licensing.
isadorara /
movie-randomizer
A documented vanilla JavaScript TMDB movie picker with a clear UI and core search/randomization flow, but no tests or CI and several incomplete interaction paths limit reliability and adoption.
isadorara /
skills-introduction-to-github
A polished GitHub Skills exercise clone with instructional Markdown and event-driven workflows, but no original application code, tests, or demonstrated adoption.
isadorara /
python-blackjack
A documented, runnable single-file Python CLI blackjack game with input validation and cross-platform screen clearing, but no tests, CI, typing, license, or evidence of adoption.
isadorara /
xylophone
A small, clearly documented browser xylophone with eight playable notes, mouse and keyboard input, and bundled MP3 sounds; it is functional but an initial one-shot project with no adoption or engineering infrastructure.
isadorara /
isadorara
A small GitHub profile repository centered on README.md and a custom banner.svg; it has no application source, tests, CI, license, or evidence of external adoption.
06 · Timeline
- Oct 11, 2024Joined GitHub
- Aug 4, 2025Created python-blackjack — A game of Blackjack coded in Python
- Jul 31, 2026Created xylophone — A simple browser-based xylophone
- Aug 6, 2026Created planner-financeiro — Aplicação de planejamento financeiro pessoal para controlar gastos via CSV ou input manual, com tabela, totais e gráficos.
- Aug 8, 2026Created isadorara
- Aug 18, 2026Created movie-randomizer — A simple app to help you pick what to watch. Add movies to a list and let it randomly choose one for you, pulling posters, synopsis, and details from the TMDB API.
- Aug 25, 2026Created weather-app — A simple web app that shows the current temperature, humidity, and wind speed for any city you search.
- Sep 9, 2026Created skills-introduction-to-github — My clone repository
- Sep 22, 2026Most recent push to planner-financeiro
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.