[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFEK2MJ3C166PKCCTMRHHN":3,"skill-same:01M6AFEK2MJ3C166PKCCTMRHHN":86},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M6AFEK2MJ3C166PKCCTMRHHN","get-available-resources",null,"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.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fget-available-resources\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"resources","get available resources","get","parallel","running","at","information","GPU Acceleration","CPU","processing","scientific","as","recommendations","computational","strategies","memory","disk","dask","constraints","Memory-Efficient","start","file","gpu","report","core","training","pytorch","2026-11-10 10:12:30",false,"---\nname: get-available-resources\ndescription: 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.\n---\n\n# Get Available Resources\n\n## Overview\n\nDetect 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.\n\n## When to Use This Skill\n\nUse this skill proactively before any computationally intensive task:\n\n- **Before data analysis**: Determine if datasets can be loaded into memory or require out-of-core processing\n- **Before model training**: Check if GPU acceleration is available and which backend to use\n- **Before parallel processing**: Identify optimal number of workers for joblib, multiprocessing, or Dask\n- **Before large file operations**: Verify sufficient disk space and appropriate storage strategies\n- **At project initialization**: Understand baseline capabilities for making architectural decisions\n\n**Example scenarios:**\n- \"Help me analyze this 50GB genomics dataset\" → Use this skill first to determine if Dask\u002FZarr are needed\n- \"Train a neural network on this data\" → Use this skill to detect available GPUs and backends\n- \"Process 10,000 files in parallel\" → Use this skill to determine optimal worker count\n- \"Run a computationally intensive simulation\" → Use this skill to understand resource constraints\n\n## How This Skill Works\n\n### Resource Detection\n\nThe skill runs `scripts\u002Fdetect_resources.py` to automatically detect:\n\n1. **CPU Information**\n   - Physical and logical core counts\n   - Processor architecture and model\n   - CPU frequency information\n\n2. **GPU Information**\n   - NVIDIA GPUs: Detects via nvidia-smi, reports VRAM, driver version, compute capability\n   - AMD GPUs: Detects via rocm-smi\n   - Apple Silicon: Detects M1\u002FM2\u002FM3\u002FM4 chips with Metal support and unified memory\n\n3. **Memory Information**\n   - Total and available RAM\n   - Current memory usage percentage\n   - Swap space availability\n\n4. **Disk Space Information**\n   - Total and available disk space for working directory\n   - Current usage percentage\n\n5. **Operating System Information**\n   - OS type (macOS, Linux, Windows)\n   - OS version and release\n   - Python version\n\n### Output Format\n\nThe skill generates a `.claude_resources.json` file in the current working directory containing:\n\n```json\n{\n  \"timestamp\": \"2025-10-23T10:30:00\",\n  \"os\": {\n    \"system\": \"Darwin\",\n    \"release\": \"25.0.0\",\n    \"machine\": \"arm64\"\n  },\n  \"cpu\": {\n    \"physical_cores\": 8,\n    \"logical_cores\": 8,\n    \"architecture\": \"arm64\"\n  },\n  \"memory\": {\n    \"total_gb\": 16.0,\n    \"available_gb\": 8.5,\n    \"percent_used\": 46.9\n  },\n  \"disk\": {\n    \"total_gb\": 500.0,\n    \"available_gb\": 200.0,\n    \"percent_used\": 60.0\n  },\n  \"gpu\": {\n    \"nvidia_gpus\": [],\n    \"amd_gpus\": [],\n    \"apple_silicon\": {\n      \"name\": \"Apple M2\",\n      \"type\": \"Apple Silicon\",\n      \"backend\": \"Metal\",\n      \"unified_memory\": true\n    },\n    \"total_gpus\": 1,\n    \"available_backends\": [\"Metal\"]\n  },\n  \"recommendations\": {\n    \"parallel_processing\": {\n      \"strategy\": \"high_parallelism\",\n      \"suggested_workers\": 6,\n      \"libraries\": [\"joblib\", \"multiprocessing\", \"dask\"]\n    },\n    \"memory_strategy\": {\n      \"strategy\": \"moderate_memory\",\n      \"libraries\": [\"dask\", \"zarr\"],\n      \"note\": \"Consider chunking for datasets > 2GB\"\n    },\n    \"gpu_acceleration\": {\n      \"available\": true,\n      \"backends\": [\"Metal\"],\n      \"suggested_libraries\": [\"pytorch-mps\", \"tensorflow-metal\", \"jax-metal\"]\n    },\n    \"large_data_handling\": {\n      \"strategy\": \"disk_abundant\",\n      \"note\": \"Sufficient space for large intermediate files\"\n    }\n  }\n}\n```\n\n### Strategic Recommendations\n\nThe skill generates context-aware recommendations:\n\n**Parallel Processing Recommendations:**\n- **High parallelism (8+ cores)**: Use Dask, joblib, or multiprocessing with workers = cores - 2\n- **Moderate parallelism (4-7 cores)**: Use joblib or multiprocessing with workers = cores - 1\n- **Sequential (\u003C 4 cores)**: Prefer sequential processing to avoid overhead\n\n**Memory Strategy Recommendations:**\n- **Memory constrained (\u003C 4GB available)**: Use Zarr, Dask, or H5py for out-of-core processing\n- **Moderate memory (4-16GB available)**: Use Dask\u002FZarr for datasets > 2GB\n- **Memory abundant (> 16GB available)**: Can load most datasets into memory directly\n\n**GPU Acceleration Recommendations:**\n- **NVIDIA GPUs detected**: Use PyTorch, TensorFlow, JAX, CuPy, or RAPIDS\n- **AMD GPUs detected**: Use PyTorch-ROCm or TensorFlow-ROCm\n- **Apple Silicon detected**: Use PyTorch with MPS backend, TensorFlow-Metal, or JAX-Metal\n- **No GPU detected**: Use CPU-optimized libraries\n\n**Large Data Handling Recommendations:**\n- **Disk constrained (\u003C 10GB)**: Use streaming or compression strategies\n- **Moderate disk (10-100GB)**: Use Zarr, H5py, or Parquet formats\n- **Disk abundant (> 100GB)**: Can create large intermediate files freely\n\n## Usage Instructions\n\n### Step 1: Run Resource Detection\n\nExecute the detection script at the start of any computationally intensive task:\n\n```bash\npython scripts\u002Fdetect_resources.py\n```\n\nOptional arguments:\n- `-o, --output \u003Cpath>`: Specify custom output path (default: `.claude_resources.json`)\n- `-v, --verbose`: Print full resource information to stdout\n\n### Step 2: Read and Apply Recommendations\n\nAfter running detection, read the generated `.claude_resources.json` file to inform computational decisions:\n\n```python\n# Example: Use recommendations in code\nimport json\n\nwith open('.claude_resources.json', 'r') as f:\n    resources = json.load(f)\n\n# Check parallel processing strategy\nif resources['recommendations']['parallel_processing']['strategy'] == 'high_parallelism':\n    n_jobs = resources['recommendations']['parallel_processing']['suggested_workers']\n    # Use joblib, Dask, or multiprocessing with n_jobs workers\n\n# Check memory strategy\nif resources['recommendations']['memory_strategy']['strategy'] == 'memory_constrained':\n    # Use Dask, Zarr, or H5py for out-of-core processing\n    import dask.array as da\n    # Load data in chunks\n\n# Check GPU availability\nif resources['recommendations']['gpu_acceleration']['available']:\n    backends = resources['recommendations']['gpu_acceleration']['backends']\n    # Use appropriate GPU library based on available backend\n```\n\n### Step 3: Make Informed Decisions\n\nUse the resource information and recommendations to make strategic choices:\n\n**For data loading:**\n```python\nmemory_available_gb = resources['memory']['available_gb']\ndataset_size_gb = 10\n\nif dataset_size_gb > memory_available_gb * 0.5:\n    # Dataset is large relative to memory, use Dask\n    import dask.dataframe as dd\n    df = dd.read_csv('large_file.csv')\nelse:\n    # Dataset fits in memory, use pandas\n    import pandas as pd\n    df = pd.read_csv('large_file.csv')\n```\n\n**For parallel processing:**\n```python\nfrom joblib import Parallel, delayed\n\nn_jobs = resources['recommendations']['parallel_processing'].get('suggested_workers', 1)\n\nresults = Parallel(n_jobs=n_jobs)(\n    delayed(process_function)(item) for item in data\n)\n```\n\n**For GPU acceleration:**\n```python\nimport torch\n\nif 'CUDA' in resources['gpu']['available_backends']:\n    device = torch.device('cuda')\nelif 'Metal' in resources['gpu']['available_backends']:\n    device = torch.device('mps')\nelse:\n    device = torch.device('cpu')\n\nmodel = model.to(device)\n```\n\n## Dependencies\n\nThe detection script requires the following Python packages:\n\n```bash\nuv pip install psutil\n```\n\nAll other functionality uses Python standard library modules (json, os, platform, subprocess, sys, pathlib).\n\n## Platform Support\n\n- **macOS**: Full support including Apple Silicon (M1\u002FM2\u002FM3\u002FM4) GPU detection\n- **Linux**: Full support including NVIDIA (nvidia-smi) and AMD (rocm-smi) GPU detection\n- **Windows**: Full support including NVIDIA GPU detection\n\n## Best Practices\n\n1. **Run early**: Execute resource detection at the start of projects or before major computational tasks\n2. **Re-run periodically**: System resources change over time (memory usage, disk space)\n3. **Check before scaling**: Verify resources before scaling up parallel workers or data sizes\n4. **Document decisions**: Keep the `.claude_resources.json` file in project directories to document resource-aware decisions\n5. **Use with versioning**: Different machines have different capabilities; resource files help maintain portability\n\n## Troubleshooting\n\n**GPU not detected:**\n- Ensure GPU drivers are installed (nvidia-smi, rocm-smi, or system_profiler for Apple Silicon)\n- Check that GPU utilities are in system PATH\n- Verify GPU is not in use by other processes\n\n**Script execution fails:**\n- Ensure psutil is installed: `uv pip install psutil`\n- Check Python version compatibility (Python 3.6+)\n- Verify script has execute permissions: `chmod +x scripts\u002Fdetect_resources.py`\n\n**Inaccurate memory readings:**\n- Memory readings are snapshots; actual available memory changes constantly\n- Close other applications before detection for accurate \"available\" memory\n- Consider running detection multiple times and averaging results\n","# Get Available Resources\n\n## Overview\n\nDetect 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.\n\n## When to Use This Skill\n\nUse this skill proactively before any computationally intensive task:\n\n- **Before data analysis**: Determine if datasets can be loaded into memory or require out-of-core processing\n- **Before model training**: Check if GPU acceleration is available and which backend to use\n- **Before parallel processing**: Identify optimal number of workers for joblib, multiprocessing, or Dask\n- **Before large file operations**: Verify sufficient disk space and appropriate storage strategies\n- **At project initialization**: Understand baseline capabilities for making architectural decisions\n\n**Example scenarios:**\n- \"Help me analyze this 50GB genomics dataset\" → Use this skill first to determine if Dask\u002FZarr are needed\n- \"Train a neural network on this data\" → Use this skill to detect available GPUs and backends\n- \"Process 10,000 files in parallel\" → Use this skill to determine optimal worker count\n- \"Run a computationally intensive simulation\" → Use this skill to understand resource constraints\n\n## How This Skill Works\n\n### Resource Detection\n\nThe skill runs `scripts\u002Fdetect_resources.py` to automatically detect:\n\n1. **CPU Information**\n   - Physical and logical core counts\n   - Processor architecture and model\n   - CPU frequency information\n\n2. **GPU Information**\n   - NVIDIA GPUs: Detects via nvidia-smi, reports VRAM, driver version, compute capability\n   - AMD GPUs: Detects via rocm-smi\n   - Apple Silicon: Detects M1\u002FM2\u002FM3\u002FM4 chips with Metal support and unified memory\n\n3. **Memory Information**\n   - Total and available RAM\n   - Current memory usage percentage\n   - Swap space availability\n\n4. **Disk Space Information**\n   - Total and available disk space for working directory\n   - Current usage percentage\n\n5. **Operating System Information**\n   - OS type (macOS, Linux, Windows)\n   - OS version and release\n   - Python version\n\n### Output Format\n\nThe skill generates a `.claude_resources.json` file in the current working directory containing:\n\n```json\n{\n  \"timestamp\": \"2025-10-23T10:30:00\",\n  \"os\": {\n    \"system\": \"Darwin\",\n    \"release\": \"25.0.0\",\n    \"machine\": \"arm64\"\n  },\n  \"cpu\": {\n    \"physical_cores\": 8,\n    \"logical_cores\": 8,\n    \"architecture\": \"arm64\"\n  },\n  \"memory\": {\n    \"total_gb\": 16.0,\n    \"available_gb\": 8.5,\n    \"percent_used\": 46.9\n  },\n  \"disk\": {\n    \"total_gb\": 500.0,\n    \"available_gb\": 200.0,\n    \"percent_used\": 60.0\n  },\n  \"gpu\": {\n    \"nvidia_gpus\": [],\n    \"amd_gpus\": [],\n    \"apple_silicon\": {\n      \"name\": \"Apple M2\",\n      \"type\": \"Apple Silicon\",\n      \"backend\": \"Metal\",\n      \"unified_memory\": true\n    },\n    \"total_gpus\": 1,\n    \"available_backends\": [\"Metal\"]\n  },\n  \"recommendations\": {\n    \"parallel_processing\": {\n      \"strategy\": \"high_parallelism\",\n      \"suggested_workers\": 6,\n      \"libraries\": [\"joblib\", \"multiprocessing\", \"dask\"]\n    },\n    \"memory_strategy\": {\n      \"strategy\": \"moderate_memory\",\n      \"libraries\": [\"dask\", \"zarr\"],\n      \"note\": \"Consider chunking for datasets > 2GB\"\n    },\n    \"gpu_acceleration\": {\n      \"available\": true,\n      \"backends\": [\"Metal\"],\n      \"suggested_libraries\": [\"pytorch-mps\", \"tensorflow-metal\", \"jax-metal\"]\n    },\n    \"large_data_handling\": {\n      \"strategy\": \"disk_abundant\",\n      \"note\": \"Sufficient space for large intermediate files\"\n    }\n  }\n}\n```\n\n### Strategic Recommendations\n\nThe skill generates context-aware recommendations:\n\n**Parallel Processing Recommendations:**\n- **High parallelism (8+ cores)**: Use Dask, joblib, or multiprocessing with workers = cores - 2\n- **Moderate parallelism (4-7 cores)**: Use joblib or multiprocessing with workers = cores - 1\n- **Sequential (\u003C 4 cores)**: Prefer sequential processing to avoid overhead\n\n**Memory Strategy Recommendations:**\n- **Memory constrained (\u003C 4GB available)**: Use Zarr, Dask, or H5py for out-of-core processing\n- **Moderate memory (4-16GB available)**: Use Dask\u002FZarr for datasets > 2GB\n- **Memory abundant (> 16GB available)**: Can load most datasets into memory directly\n\n**GPU Acceleration Recommendations:**\n- **NVIDIA GPUs detected**: Use PyTorch, TensorFlow, JAX, CuPy, or RAPIDS\n- **AMD GPUs detected**: Use PyTorch-ROCm or TensorFlow-ROCm\n- **Apple Silicon detected**: Use PyTorch with MPS backend, TensorFlow-Metal, or JAX-Metal\n- **No GPU detected**: Use CPU-optimized libraries\n\n**Large Data Handling Recommendations:**\n- **Disk constrained (\u003C 10GB)**: Use streaming or compression strategies\n- **Moderate disk (10-100GB)**: Use Zarr, H5py, or Parquet formats\n- **Disk abundant (> 100GB)**: Can create large intermediate files freely\n\n## Usage Instructions\n\n### Step 1: Run Resource Detection\n\nExecute the detection script at the start of any computationally intensive task:\n\n```bash\npython scripts\u002Fdetect_resources.py\n```\n\nOptional arguments:\n- `-o, --output \u003Cpath>`: Specify custom output path (default: `.claude_resources.json`)\n- `-v, --verbose`: Print full resource information to stdout\n\n### Step 2: Read and Apply Recommendations\n\nAfter running detection, read the generated `.claude_resources.json` file to inform computational decisions:\n\n```python\n# Example: Use recommendations in code\nimport json\n\nwith open('.claude_resources.json', 'r') as f:\n    resources = json.load(f)\n\n# Check parallel processing strategy\nif resources['recommendations']['parallel_processing']['strategy'] == 'high_parallelism':\n    n_jobs = resources['recommendations']['parallel_processing']['suggested_workers']\n    # Use joblib, Dask, or multiprocessing with n_jobs workers\n\n# Check memory strategy\nif resources['recommendations']['memory_strategy']['strategy'] == 'memory_constrained':\n    # Use Dask, Zarr, or H5py for out-of-core processing\n    import dask.array as da\n    # Load data in chunks\n\n# Check GPU availability\nif resources['recommendations']['gpu_acceleration']['available']:\n    backends = resources['recommendations']['gpu_acceleration']['backends']\n    # Use appropriate GPU library based on available backend\n```\n\n### Step 3: Make Informed Decisions\n\nUse the resource information and recommendations to make strategic choices:\n\n**For data loading:**\n```python\nmemory_available_gb = resources['memory']['available_gb']\ndataset_size_gb = 10\n\nif dataset_size_gb > memory_available_gb * 0.5:\n    # Dataset is large relative to memory, use Dask\n    import dask.dataframe as dd\n    df = dd.read_csv('large_file.csv')\nelse:\n    # Dataset fits in memory, use pandas\n    import pandas as pd\n    df = pd.read_csv('large_file.csv')\n```\n\n**For parallel processing:**\n```python\nfrom joblib import Parallel, delayed\n\nn_jobs = resources['recommendations']['parallel_processing'].get('suggested_workers', 1)\n\nresults = Parallel(n_jobs=n_jobs)(\n    delayed(process_function)(item) for item in data\n)\n```\n\n**For GPU acceleration:**\n```python\nimport torch\n\nif 'CUDA' in resources['gpu']['available_backends']:\n    device = torch.device('cuda')\nelif 'Metal' in resources['gpu']['available_backends']:\n    device = torch.device('mps')\nelse:\n    device = torch.device('cpu')\n\nmodel = model.to(device)\n```\n\n## Dependencies\n\nThe detection script requires the following Python packages:\n\n```bash\nuv pip install psutil\n```\n\nAll other functionality uses Python standard library modules (json, os, platform, subprocess, sys, pathlib).\n\n## Platform Support\n\n- **macOS**: Full support including Apple Silicon (M1\u002FM2\u002FM3\u002FM4) GPU detection\n- **Linux**: Full support including NVIDIA (nvidia-smi) and AMD (rocm-smi) GPU detection\n- **Windows**: Full support including NVIDIA GPU detection\n\n## Best Practices\n\n1. **Run early**: Execute resource detection at the start of projects or before major computational tasks\n2. **Re-run periodically**: System resources change over time (memory usage, disk space)\n3. **Check before scaling**: Verify resources before scaling up parallel workers or data sizes\n4. **Document decisions**: Keep the `.claude_resources.json` file in project directories to document resource-aware decisions\n5. **Use with versioning**: Different machines have different capabilities; resource files help maintain portability\n\n## Troubleshooting\n\n**GPU not detected:**\n- Ensure GPU drivers are installed (nvidia-smi, rocm-smi, or system_profiler for Apple Silicon)\n- Check that GPU utilities are in system PATH\n- Verify GPU is not in use by other processes\n\n**Script execution fails:**\n- Ensure psutil is installed: `uv pip install psutil`\n- Check Python version compatibility (Python 3.6+)\n- Verify script has execute permissions: `chmod +x scripts\u002Fdetect_resources.py`\n\n**Inaccurate memory readings:**\n- Memory readings are snapshots; actual available memory changes constantly\n- Close other applications before detection for accurate \"available\" memory\n- Consider running detection multiple times and averaging results\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fget-available-resources",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add davila7\u002Fclaude-code-templates --skill get-available-resources",{"tool":72,"command":73},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill get-available-resources",{"tool":75,"command":76},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill get-available-resources","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fget-available-resources\u002FSKILL.md",true,[80],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Fdetect_resources.py","SCRIPT","脚本",14081,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fget-available-resources\u002Fscripts\u002Fdetect_resources.py",[87,115,142,175,209,233],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":94,"publishedAt":51},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[93],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":51},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[121],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[123,124,125,126,127,128,129,130,131,132,133,104,134,135,136,137,138,139,140,141],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":157,"publishedAt":51},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[148,151,152],{"categoryNo":149,"categoryName":150,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[158,159,160,161,162,163,164,100,165,166,167,168,169,170,171,103,172,173,104,174],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":179,"licenseFileUrl":180,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":51},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[187,188,189,190,191,192,193,194,195,196,197,198,199,45,200,201,202,203,204,205,206,207,100,208],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":179,"licenseFileUrl":213,"sourceHtmlUrl":214,"categories":215,"keywords":220,"publishedAt":51},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[216,219],{"categoryNo":217,"categoryName":218,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},[221,222,223,224,225,188,226,197,198,227,228,229,230,100,231,106,232],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":234,"name":235,"nameZh":6,"description":236,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":179,"licenseFileUrl":237,"sourceHtmlUrl":238,"categories":239,"keywords":247,"publishedAt":51},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[240,243,244],{"categoryNo":241,"categoryName":242,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":245,"categoryName":246,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000036","内容创作者",[248,249,250,251,252,253,254,255,190,256,45,134,257,258,259,260,261,170,262,104,263,264,265,266,267,112,36],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble"]