monitor-experiment

仓库创建 2026年3月10日最近提交 5 天前SkillHot 收录 20 天前
▸ 精选理由

适合需要自动轮询并收集实验产出的科研/工程流水线场景。

▸ 风险提示

需访问外部作业/存储系统,可能涉及凭证与数据访问权限风险。

这个 Skill 做什么

监控运行实验、检查进度并收集可机器验证的结果输出。

监控正在跑的实验,帮你自动查看进度并把可机器验证的输出(比如退出码、文件是否存在、时间戳)收集起来。想知道“做完了吗”“结果在哪儿”或要拿到可自动验证的产出时用。特点是只检查能被机器判定的完成条件,不做质量评估,适合外部定时或后台等待场景。

▸ 展开 SKILL.md 英文原文

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

研究检索实验监控结果收集进度检查通用
1.4w
Stars
1.2k
Forks
40
仓库内 Skill
+844
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/main/skills/monitor-experiment/SKILL.md
或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/main/skills/monitor-experiment/SKILL.md"
SKILL.MD 节选查看完整文件 ↗
# Monitor Experiment Results

> ⏱ **External cadence is appropriate here.** This skill waits on an external
> fact (job completion / progress), so it is a natural `/loop` / `CronCreate`
> surface: the wake reads status and self-judges only **machine-checkable**
> completion (exit code, file exists, epoch logged) — never quality. This is
> the additive external-wait shape in
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
> If a scheduled wait here ends in a verdict step (e.g. then audit results),
> run that verdict **once** after the wait clears — not re-entered per tick.

Monitor: $ARGUMENTS

## Workflow

### Step 1: Check What's Running

**SSH server:
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有