菜单
Frames a data/ML problem before any modeling — the decision, the action, the cost of a wrong call, task type, target, and success metric. Use when picking a project direction, writing a research question, or mapping a problem onto an ML task type.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
| name | framing-ml-problems |
| description | Frames a data/ML problem before any modeling — the decision, the action, the cost of a wrong call, task type, target, and success metric. Use when picking a project direction, writing a research question, or mapping a problem onto an ML task type. |
A model is never the goal. A better DECISION is the goal. Frame first, model later.
| If your question sounds like… | Task type | Target | Typical metric |
|---|---|---|---|
| "Which ones first?" | Ranking / scoring | a priority score | precision@K |
| "Will this one decline / recover?" | Classification | a yes/no label from an OBSERVED outcome | ROC-AUC, precision/recall vs base rate |
| "What kinds of items exist?" | Clustering | none (unsupervised) | silhouette + human sense-check |
| "Which signals travel together?" | Signal analysis | none | effect sizes, grouped comparisons |
Two rules that save whole projects:
For [who], deciding [what], we will build [output type] from [data], predicting/scoring [target] measured by [metric]. A wrong call costs [cost]. A plain rule isn't enough because [why]. We will claim only [observed / directional / decision-support] results.
If you can fill that paragraph honestly, you are framed. If a blank stays blank, that blank IS your next task.
