メニュー
Deploys a static page (research paper, portfolio piece) for free from a GitHub repo using GitHub Pages — setup, file layout, verification, and recording the final URL. Use when publishing a finished write-up as a public web page.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Finds label leakage and designs honest validation — leakage taxonomy, grouped and time-aware splits, base rates, and the attack-your-own-model checklist. Use before trusting any metric, when a score looks too good, or when features and labels share time windows or origins.
The FlyRank internship datasets — the 30k-row starter CSV and its gotchas, the ~79M-row warehouse release tables and grains, panel warnings, access, and iteration rules. Load for EVERY task that touches the data. (Project-specific: delete this folder when reusing the skill library elsewhere.)
Works with datasets far too big to download or load in pandas — SQL over remote Parquet with DuckDB, aggregate-then-model, iterate on samples. Use when a dataset has millions of rows, lives on a remote host (hf:// or s3), or a notebook runs out of memory or hits rate limits.
Runs an honest EDA and signal audit — distributions first, heavy-tail handling, verdict-style mini-tests (CONFIRMED/OPPOSITE/MIXED/FALSE), sample-size floors. Use before modeling, when testing whether a popular belief shows up in data, or when a correlation looks too good.
Builds the transparent rule-based baseline every model must beat — a hand-written score with reason codes, ranked output, and precision@K evaluation. Use before training any model, or when someone reports model results with nothing to compare against.
Teaches the working method for using an AI coding assistant on analysis tasks — one task per fresh conversation, search before assuming, interview before big plans, validate everything, commit per finished task. Use at the start of any assignment, whenever a conversation gets long and confused, or when the assistant starts guessing.
| name | deploying-static-pages |
| description | Deploys a static page (research paper, portfolio piece) for free from a GitHub repo using GitHub Pages — setup, file layout, verification, and recording the final URL. Use when publishing a finished write-up as a public web page. |
Your repo can BE your website. GitHub Pages serves files from your repo at a public URL — free, no new accounts, done in ten minutes.
index.html in a docs/ folder of your repo (a
paper/ exported to HTML also works — the folder just has to contain index.html).
Keep assets (images, css) in the same folder with RELATIVE paths (img/chart1.png,
not /Users/you/...).main,
Folder: /docs → Save.https://<your-username>.github.io/<repo-name>/
(Settings → Pages shows the exact URL once it's live).submission/paper_url.txt (nothing else in the file).jupyter nbconvert --to html capstone.ipynb, rename to index.html,
put it in docs/ — then still write a proper abstract at the top.submission/paper_url.txt contains exactly that URL, one line, starts with https://.