run-experiment
Deploy and run ML experiments on local or remote GPU servers. Use when user says \"run experiment\", \"deploy to server\", \"\u8dd1\u5b9e\u9a8c\", or needs to launch training jobs.
npx skills add majiayu000/claude-skill-registry --skill run-experiment-wanshuiyin-auto-claude-code-res --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.
# Run Experiment Deploy and run ML experiment: $ARGUMENTS ## Workflow ### Step 1: Detect Environment Read the project's `AGENTS.md` to determine the experiment environment: - **Local GPU**: Look for local CUDA/MPS setup info - **Remote server**: Look for SSH alias, conda env, code directory - **Vast.ai instance**: Look for `gpu: vast`, `vast_instance`, SSH host/port, remote path, and optional `auto_destroy` - **Modal serverless**: Look for `gpu: modal`, app/function name, image/dependency setup, and secrets If no server info is found in `AGENTS.md`, ask the user. ### Step 2: Pre-flight Check Check GPU availability on the target machine: **Remote:** ```bash ssh <server> nvidia-smi --query-gpu=index,memory.used,memory.total --format=csv,noheader ``` **Local:** ```bash nvidia-smi --query-gpu=index,memory.used,memory.total --format=csv,noheader # or for Mac MPS: python -c "import torch; print('MPS available:', torch.backends.mps.is_available())" ``` Free GPU = memory.used < 500 MiB. ### Step 3: Sync Code (Remote Only) Check the project's `AGENTS.md` for a `code_sync` setting. If not specified, default to `rsync`. #### Option A: rsync (default) Only sync necessary files — NOT data, chec
- Workflow
- Step 1: Detect Environment
- Step 2: Pre-flight Check
- Step 3: Sync Code (Remote Only)
- Step 3.5: W&B Integration (when wandb: true in AGENTS.md)
- Step 4: Deploy
- Step 5: Verify Launch
- Step 6: Feishu Notification (if configured)
- Step 7: Auto-Destroy Vast.ai Instance (when gpu: vast and autodestroy: true)
- Key Rules
- AGENTS.md Example
ssh <server> nvidia-smi --query-gpu=index,memory.used,memory.total --format=csv,noheader
nvidia-smi --query-gpu=index,memory.used,memory.total --format=csv,noheader
or for Mac MPS:
python -c "import torch; print('MPS available:', torch.backends.mps.is_available())"
rsync -avz --include='*.py' --exclude='*' <local_src>/ <server>:<remote_dst>/
git add -A && git commit -m "sync: experiment deployment" && git push
ssh <server> "cd <remote_dst> && git pull"
ssh <server> "wandb status" # should show logged in
ssh <server> "wandb login <WANDB_API_KEY>"
ssh <server> "screen -dmS <exp_name> bash -c '\What does the run-experiment skill do?
Deploy and run ML experiments on local or remote GPU servers. Use when user says \"run experiment\", \"deploy to server\", \"\u8dd1\u5b9e\u9a8c\", or needs to launch training jobs.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill run-experiment-wanshuiyin-auto-claude-code-res --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 majiayu000/claude-skill-registry, a repository with 534 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.