prai-experiments
100 / 100 · Low risk
Fine to try.
在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 设计与呈现模式识别/机器学习实验证据时调用。覆盖研究问题(RQ)拆解、公平基线与相同划分/算力、评测指标选择(准确率/F1/mAP/IoU/AUC 等)、多次运行的均值±标准差与统计显著性检验、消融实验、复杂度与开销报告、数据泄漏与评测污染的防范,以及把每条主张绑定到证据的呈现方式。用于把 AI 细分方向的实证部分做到经得起外审对"基线是否公平、结果是否可信、消融是否充分"的质询。
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'prai-experiments' ] || [ -L ~/.agents/skills/'prai-experiments' ]; then echo 'A skill folder named prai-experiments already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/brycewang-stanford/Awesome-Journal-Skills' "$d" && git -C "$d" checkout --quiet '932eb23331721b16e967c59f093781be1928b498' -- 'Pattern-Recognition-and-Artificial-Intelligence-Skills/skills/prai-experiments' && mkdir -p ~/.agents/skills && cp -R "$d"/'Pattern-Recognition-and-Artificial-Intelligence-Skills/skills/prai-experiments' ~/.agents/skills/'prai-experiments' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'prai-experiments' ~/.claude/skills/'prai-experiments' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/brycewang-stanford/Awesome-Journal-Skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | 932eb23 | 100 |
| 2026-11-07 | 932eb23 | 100 |