monitor-experiment
Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill monitor-experiment --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Monitor Experiment Results Monitor: $ARGUMENTS ## Workflow ### Step 1: Check What's Running **SSH server:** ```bash ssh <server> "screen -ls" ``` **Vast.ai instance** (read `ssh_host`, `ssh_port` from `vast-instances.json`): ```bash ssh -p <PORT> root@<HOST> "screen -ls" ``` Also check vast.ai instance status: ```bash vastai show instances ``` ### Step 2: Collect Output from Each Screen For each screen session, capture the last N lines: ```bash ssh <server> "screen -S <name> -X hardcopy /tmp/screen_<name>.txt && tail -50 /tmp/screen_<name>.txt" ``` If hardcopy fails, check for log files or tee output. ### Step 3: Check for JSON Result Files ```bash ssh <server> "ls -lt <results_dir>/*.json 2>/dev/null | head -20" ``` If JSON results exist, fetch and parse them: ```bash ssh <server> "cat <results_dir>/<latest>.json" ``` ### Step 3.5: Pull W&B Metrics (when `wandb: true` in CLAUDE.md) **Skip this step entirely if `wandb` is not set or is `false` in CLAUDE.md.** Pull training curves and metrics from Weights & Biases via Python API: ```bash # List recent runs in the project ssh <server> "python3 -c \" import wandb api = wandb.Api() runs = api.runs('<entity>/<project>', per_page=10) f
- Workflow
- Step 1: Check What's Running
- Step 2: Collect Output from Each Screen
- Step 3: Check for JSON Result Files
- Step 3.5: Pull W&B Metrics (when wandb: true in CLAUDE.md)
- Step 4: Summarize Results
- Step 5: Interpret
- Step 6: Feishu Notification (if configured)
- Key Rules
ssh <server> "screen -ls" ssh -p <PORT> root@<HOST> "screen -ls" vastai show instances ssh <server> "screen -S <name> -X hardcopy /tmp/screen_<name>.txt && tail -50 /tmp/screen_<name>.txt" ssh <server> "ls -lt <results_dir>/*.json 2>/dev/null | head -20" ssh <server> "cat <results_dir>/<latest>.json" List recent runs in the project ssh <server> "python3 -c \" import wandb api = wandb.Api()
What does the monitor-experiment skill do?
Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill monitor-experiment --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.