← All skills

ope-rs-experiment-execution

95 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By pdl-openair/OpenAIR (GitHub) · coding · 16 stars · scanned at commit cb37612

当用户想要运行 OPE 实验、批量评估估计器、或管理实验任务时自动触发。常见场景：用户说"跑 OPE 实验"、"执行批量评估"、"批量运行 FQE"。本 skill 完成批量执行、日志记录、失败重试，不负责代码实现与数据清洗。

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'ope-rs-experiment-execution' ] || [ -L ~/.agents/skills/'ope-rs-experiment-execution' ]; then echo 'A skill folder named ope-rs-experiment-execution already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/pdl-openair/OpenAIR' "$d" && git -C "$d" checkout --quiet 'cb37612d98d6155a133121a1f0d7cd3e06c985a8' -- 'skills/ope/ope-rs-experiment-execution' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/ope/ope-rs-experiment-execution' ~/.agents/skills/'ope-rs-experiment-execution' && 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/'ope-rs-experiment-execution' ~/.claude/skills/'ope-rs-experiment-execution' (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

The badge for pdl-openair/OpenAIR shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/pdl-openair/OpenAIR.svg)](https://zalavijaysinh.github.io/skilltrust/repos/pdl-openair/OpenAIR/)

Score history