Get Available ResourcesSAFE

Kosmos: An AI Scientist for Autonomous Discovery - An implementation and adaptation to be driven by Claude Code or API - Based on the Kosmos AI Paper - https://arxiv.org/abs/2511.02824

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: get-available-resources
description: This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
---

# Get Available Resources

## Overview

Detect available computational resources and generate strategic recommendations for scientific computing tasks. This skill automatically identifies CPU capabilities, GPU availability (NVIDIA CUDA, AMD ROCm, Apple Silicon Metal), memory constraints, and disk space to help make informed decisions about computational approaches.

## When to Use This Skill

Use this skill proactively before any computationally intensive task:

- **Before data analysis**: Determine if datasets can be loaded into memory or require out-of-core processing
- **Before model training**: Check if GPU acceleration is available and which backend to use
- **Before parallel processing**: Identify optimal number of workers for joblib, multiprocessing, or Dask
- **Before large file operations**: Verify sufficient disk space and appropriate storage strategies
- **At project initialization**: Understand baseline capabilities for making architectural decisions

**Example scenarios:**
- "Help me analyze this 50GB genomics dataset" → Use this skill first to determine if Dask/Zarr are needed
- "Train a neural network on this data" → Use this skill to detect available GPUs and backends
- "Process 10,000 files in parallel" → Use this skill to determine optimal worker count
- "Run a computationally intensive simulation" → Use this skill to understand resource constraints

## How This Skill Works

### Resource Detection

The skill runs `scripts/detect_resources.py` to automatically detect:

1. **CPU Information**
   - Physical and logical core counts
   - Processor architecture and model
   - CPU frequency information

2. **GPU Information**
   - NVIDIA GPUs: Detects via nvidia-smi, reports VRAM, driver version, compute capability
   - AMD GPUs: Detects via rocm-smi
   - Apple Silicon: Detects M1/M2/M3/M4 chips with Metal support and unified memory

3. **Memory Information**
   - Total and available RAM
   - Current memory usage percentage
   - Swap space availability

4. **Disk Space Information**
   - Total and available disk space for working directory
   - Current usage percentage

5. **Operating System Information**
   - OS type (macOS, Linux, Windows)
   - OS version and release
   - Python version

### Output Format

The skill generates a `.claude_resources.json` file in the current working directory containing:

```json
{
  "timestamp": "2025-10-23T10:30:00",
  "os": {
    "system": "Darwin",
    "release": "25.0.0",
    "machine": "arm64"
  },
  "cpu": {
    "physical_cores": 8,
    "logical_cores": 8,
    "architecture": "arm64"
  },
  "memory": {
    "total_gb": 16.0,
    "available_gb": 8.5,
    "percent_used": 46.9
  },
  "disk": {
    "total_gb": 500.0,
    "available_gb": 200.0,
    "percent_used": 60.0
  },
  "gpu": {
    "nvidia_gpus": [],
    "amd_gpus": [],
    "apple_silicon": {
      "name": "Apple M2",
      "type": "Apple Silicon",
      "backend": "Metal",
      "unified_memory": true
    },
    "total_gpus": 1,
    "available_backends": ["Metal"]
  },
  "recommendations": {
    "parallel_processing": {
      "strategy": "high_parallelism",
      "suggested_workers": 6,
      "libraries": ["joblib", "multiprocessing", "dask"]
    },
    "memory_strategy": {
      "strategy": "moderate_memory",
      "libraries": ["dask", "zarr"],
      "note": "Consider chunking for datasets > 2GB"
    },
    "gpu_acceleration": {
      "available": true,
      "backends": ["Metal"],
      "suggested_libraries": ["pytorch-mps", "tensorflow-metal", "jax-metal"]
    },
    "large_data_handling": {
      "strategy": "disk_abundant",
      "note": "Sufficient space for large intermediate files"
    }
  }
}
```

### Strategic Recommendations

The skill generates context-aware recommendations:

**Parallel Processing Recommendations:**
- **High parallelism (8+ cores)**: Use Dask, joblib, or multiprocessing with workers = cores - 2
- **Moderate parallelism (4-7 cores)**: Use joblib or multiprocessing with workers = cores - 1
- **Sequential (< 4 cores)**: Prefer sequential processing to avoid overhead

**Memory Strategy Recommendations:**
- **Memory constrained (< 4GB available)**: Use Zarr, Dask, or H5py for out-of-core processing
- **Moderate memory (4-16GB available)**: Use Dask/Zarr for datasets > 2GB
- **Memory abundant (> 16GB available)**: Can load most datasets into memory directly

**GPU Acceleration Recommendations:**
- **NVIDIA GPUs detected**: Use PyTorch, TensorFlow, JAX, CuPy, or RAPIDS
- **AMD GPUs detected**: Use PyTorch-ROCm or TensorFlow-ROCm
- **Apple Silicon detected**: Use PyTorch with MPS backend, TensorFlow-Metal, or JAX-Metal
- **No GPU detected**: Use CPU-optimized libraries

**Large Data Handling Recommendations:**
- **Disk constrained (< 10GB)**: Use streaming or compression strategies
- **Moderate disk (10-100GB)**: Use Zarr, H5py, or Parquet formats
- **Disk abundant (> 100GB)**: Can create large intermediate files freely

## Usage Instructions

### Step 1: Run Resource Detection

Execute the detection script at the start of any computationally intensive task:

```bash
python scripts/detect_resources.py
```

Optional arguments:
- `-o, --output <path>`: Specify custom output path (default: `.claude_resources.json`)
- `-v, --verbose`: Print full resource information to stdout

### Step 2: Read and Apply Recommendations

After r

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.