菜单
Check BashGym system status, GPU utilization, hardware info, and aggregate statistics. Use when asked about system health, what's running, GPU usage, memory, disk space, or general system stats.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Read and control I2C and SPI peripherals on Sipeed boards (LicheeRV Nano, MaixCAM, NanoKVM).
Submit development specs, approve execution plans, monitor workers, retry failed tasks, check job status, and manage orchestration jobs. Use when asked to start a development job, check worker progress, approve a plan, retry something, or list orchestrator jobs.
Generate synthetic training data, manage seeds, preview synthesis jobs, and work with the data factory. Use when asked to generate synthetic data, create training examples, augment a dataset, manage seeds, or check factory job status.
Browse, compare, evaluate, and manage trained models. View leaderboard, trends, lineage, and artifacts. Deploy models to Ollama. Use when asked about models, model comparison, which model is best, model evaluation, deploying a model, or downloading a model.
Browse, promote, demote, classify, and generate training examples from Claude Code execution traces. Use when asked about traces, gold traces, trace counts, promoting or demoting traces, generating examples, exporting training data, or syncing traces.
Start, stop, pause, resume, and monitor model training runs. Check training progress, view metrics, and get GPU utilization during training. Use when asked to train a model, check training status, view loss curves, stop a run, or see training logs.
| name | system |
| description | Check BashGym system status, GPU utilization, hardware info, and aggregate statistics. Use when asked about system health, what's running, GPU usage, memory, disk space, or general system stats. |
Query BashGym system health and hardware information.
Quick service health check:
scripts/api.sh GET /health
Returns: {"status": "ok", "version": "..."}
Full hardware report (CPU, GPU, memory, disk):
scripts/api.sh GET /system/info
Returns GPU utilization, CUDA availability, memory usage, disk space.
Dedicated GPU endpoint:
scripts/api.sh GET /system/gpus
Cross-subsystem stats (trace counts, model counts, training runs):
scripts/api.sh GET /stats
System-recommended models based on available hardware:
scripts/api.sh GET /system/recommendations
User: "How's the system doing?" → Call /health, then /system/info for GPU/memory. Summarize key numbers.
User: "Is my GPU being used?" → Call /system/gpus. Report utilization %, memory used/total.
User: "Give me a status report" → Call /stats for counts, /system/info for hardware. Present as a concise dashboard.