@bohuyeshan/openagent-labforge-core 3.11.5 → 3.13.0

package/generated/skills-bundles/full/skills/data-analysis/experiment-monitoring/auto-claude__monitor-experiment/SKILL.md

@@ -6,58 +6,59 @@ allowed-tools: "Bash(ssh *), Bash(echo *), Read, Write, Edit"
 metadata:
   category: "data-analysis/experiment-monitoring"
 ---
-# Monitor Experiment Results
-
-Monitor: $ARGUMENTS
-
-## Workflow
-
-### Step 1: Check What's Running
-```bash
-ssh <server> "screen -ls"
-```
-
-### 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 4: Summarize Results
-
-Present results in a comparison table:
-```
-| Experiment | Metric | Delta vs Baseline | Status |
-|-----------|--------|-------------------|--------|
-| Baseline  | X.XX   | —                 | done   |
-| Method A  | X.XX   | +Y.Y              | done   |
-```
-
-### Step 5: Interpret
-- Compare against known baselines
-- Flag unexpected results (negative delta, NaN, divergence)
-- Suggest next steps based on findings
-
-### Step 6: Feishu Notification (if configured)
-
-After results are collected, check `~/.claude/feishu.json`:
-- Send `experiment_done` notification: results summary table, delta vs baseline
-- If config absent or mode `"off"`: skip entirely (no-op)
-
-## Key Rules
-- Always show raw numbers before interpretation
-- Compare against the correct baseline (same config)
-- Note if experiments are still running (check progress bars, iteration counts)
-- If results look wrong, check training logs for errors before concluding
+
+# Monitor Experiment Results
+
+Monitor: $ARGUMENTS
+
+## Workflow
+
+### Step 1: Check What's Running
+```bash
+ssh <server> "screen -ls"
+```
+
+### 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 4: Summarize Results
+
+Present results in a comparison table:
+```
+| Experiment | Metric | Delta vs Baseline | Status |
+|-----------|--------|-------------------|--------|
+| Baseline  | X.XX   | —                 | done   |
+| Method A  | X.XX   | +Y.Y              | done   |
+```
+
+### Step 5: Interpret
+- Compare against known baselines
+- Flag unexpected results (negative delta, NaN, divergence)
+- Suggest next steps based on findings
+
+### Step 6: Feishu Notification (if configured)
+
+After results are collected, check `~/.claude/feishu.json`:
+- Send `experiment_done` notification: results summary table, delta vs baseline
+- If config absent or mode `"off"`: skip entirely (no-op)
+
+## Key Rules
+- Always show raw numbers before interpretation
+- Compare against the correct baseline (same config)
+- Note if experiments are still running (check progress bars, iteration counts)
+- If results look wrong, check training logs for errors before concluding

package/generated/skills-bundles/full/skills/data-analysis/experiment-ops/auto-claude__run-experiment/SKILL.md

@@ -6,107 +6,108 @@ allowed-tools: "Bash(*), Read, Grep, Glob, Edit, Write, Agent"
 metadata:
   category: "data-analysis/experiment-ops"
 ---
-# Run Experiment
-
-Deploy and run ML experiment: $ARGUMENTS
-
-## Workflow
-
-### Step 1: Detect Environment
-
-Read the project's `CLAUDE.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
-
-If no server info is found in `CLAUDE.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)
-
-Only sync necessary files — NOT data, checkpoints, or large files:
-```bash
-rsync -avz --include='*.py' --exclude='*' <local_src>/ <server>:<remote_dst>/
-```
-
-### Step 4: Deploy
-
-#### Remote (via SSH + screen)
-
-For each experiment, create a dedicated screen session with GPU binding:
-```bash
-ssh <server> "screen -dmS <exp_name> bash -c '\
-  eval \"\$(<conda_path>/conda shell.bash hook)\" && \
-  conda activate <env> && \
-  CUDA_VISIBLE_DEVICES=<gpu_id> python <script> <args> 2>&1 | tee <log_file>'"
-```
-
-#### Local
-
-```bash
-# Linux with CUDA
-CUDA_VISIBLE_DEVICES=<gpu_id> python <script> <args> 2>&1 | tee <log_file>
-
-# Mac with MPS (PyTorch uses MPS automatically)
-python <script> <args> 2>&1 | tee <log_file>
-```
-
-For local long-running jobs, use `run_in_background: true` to keep the conversation responsive.
-
-### Step 5: Verify Launch
-
-**Remote:**
-```bash
-ssh <server> "screen -ls"
-```
-
-**Local:**
-Check process is running and GPU is allocated.
-
-### Step 6: Feishu Notification (if configured)
-
-After deployment is verified, check `~/.claude/feishu.json`:
-- Send `experiment_done` notification: which experiments launched, which GPUs, estimated time
-- If config absent or mode `"off"`: skip entirely (no-op)
-
-## Key Rules
-
-- ALWAYS check GPU availability first — never blindly assign GPUs
-- Each experiment gets its own screen session + GPU (remote) or background process (local)
-- Use `tee` to save logs for later inspection
-- Run deployment commands with `run_in_background: true` to keep conversation responsive
-- Report back: which GPU, which screen/process, what command, estimated time
-- If multiple experiments, launch them in parallel on different GPUs
-
-## CLAUDE.md Example
-
-Users should add their server info to their project's `CLAUDE.md`:
-
-```markdown
-## Remote Server
-- SSH: `ssh my-gpu-server`
-- GPU: 4x A100 (80GB each)
-- Conda: `eval "$(/opt/conda/bin/conda shell.bash hook)" && conda activate research`
-- Code dir: `/home/user/experiments/`
-
-## Local Environment
-- Mac MPS / Linux CUDA
-- Conda env: `ml` (Python 3.10 + PyTorch)
-```
+
+# Run Experiment
+
+Deploy and run ML experiment: $ARGUMENTS
+
+## Workflow
+
+### Step 1: Detect Environment
+
+Read the project's `CLAUDE.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
+
+If no server info is found in `CLAUDE.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)
+
+Only sync necessary files — NOT data, checkpoints, or large files:
+```bash
+rsync -avz --include='*.py' --exclude='*' <local_src>/ <server>:<remote_dst>/
+```
+
+### Step 4: Deploy
+
+#### Remote (via SSH + screen)
+
+For each experiment, create a dedicated screen session with GPU binding:
+```bash
+ssh <server> "screen -dmS <exp_name> bash -c '\
+  eval \"\$(<conda_path>/conda shell.bash hook)\" && \
+  conda activate <env> && \
+  CUDA_VISIBLE_DEVICES=<gpu_id> python <script> <args> 2>&1 | tee <log_file>'"
+```
+
+#### Local
+
+```bash
+# Linux with CUDA
+CUDA_VISIBLE_DEVICES=<gpu_id> python <script> <args> 2>&1 | tee <log_file>
+
+# Mac with MPS (PyTorch uses MPS automatically)
+python <script> <args> 2>&1 | tee <log_file>
+```
+
+For local long-running jobs, use `run_in_background: true` to keep the conversation responsive.
+
+### Step 5: Verify Launch
+
+**Remote:**
+```bash
+ssh <server> "screen -ls"
+```
+
+**Local:**
+Check process is running and GPU is allocated.
+
+### Step 6: Feishu Notification (if configured)
+
+After deployment is verified, check `~/.claude/feishu.json`:
+- Send `experiment_done` notification: which experiments launched, which GPUs, estimated time
+- If config absent or mode `"off"`: skip entirely (no-op)
+
+## Key Rules
+
+- ALWAYS check GPU availability first — never blindly assign GPUs
+- Each experiment gets its own screen session + GPU (remote) or background process (local)
+- Use `tee` to save logs for later inspection
+- Run deployment commands with `run_in_background: true` to keep conversation responsive
+- Report back: which GPU, which screen/process, what command, estimated time
+- If multiple experiments, launch them in parallel on different GPUs
+
+## CLAUDE.md Example
+
+Users should add their server info to their project's `CLAUDE.md`:
+
+```markdown
+## Remote Server
+- SSH: `ssh my-gpu-server`
+- GPU: 4x A100 (80GB each)
+- Conda: `eval "$(/opt/conda/bin/conda shell.bash hook)" && conda activate research`
+- Code dir: `/home/user/experiments/`
+
+## Local Environment
+- Mac MPS / Linux CUDA
+- Conda env: `ml` (Python 3.10 + PyTorch)
+```