AGENT SKILL
data-check
Review data scripts and notebooks for clarity, leakage, and reproducibility.
- License 许可
- MIT
- 所属仓库
- Zwin-ux/kit
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 2
01 前言 Front Matter
- name
- data-check
- version
- 0.1.0
- description
- Review data scripts and notebooks for clarity, leakage, and reproducibility.
- compatibility
- [ "claude-code", "grok-build", "codex" ]
03 SKILL.md 正文
Instructions
- Inspect data load paths, seeds, and train/test splits for leakage.
- Prefer small, reproducible samples over silent full-dataset runs.
- Call out missing schema docs, null handling, and unit assumptions.
- Keep notebooks linear: clear cells, no hidden state, named outputs.
- Suggest a minimal check command or test for the critical transform.
- Summarize risks and what to verify before shipping a model or report.
04 同仓库更多 Skills
concepts
暂无简介
★ 0
write-tests
Add focused tests for important project behavior.
★ 0
workspace-setup
Set up monorepo and multi-package workspaces for agents and humans.
★ 0
ship-checklist
Run a practical pre-ship checklist for an app release.
★ 0
project-setup
Set up a clean project baseline for agents and humans.
★ 0
pr-ready
Prepare a clear pull request summary, test plan, and risk notes.
★ 0