[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFCQE7N5F8B5SCZPNHPC5C":3,"skill-same:01M6AFCQE7N5F8B5SCZPNHPC5C":97},{"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":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6AFCQE7N5F8B5SCZPNHPC5C","dnanexus-integration",null,"DNAnexus cloud genomics platform. Build apps\u002Fapplets, manage data (upload\u002Fdownload), dxpy Python SDK, run workflows, FASTQ\u002FBAM\u002FVCF, for genomics pipeline development and execution.","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\u002Fdnanexus-integration\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],"integration","dnanexus integration","for","python","vcf","bam","FASTQ","apps","platform","upload","build","manage","python sdk","execution","pipeline","data","cloud","manage data","run","development","workflows","sdk","2026-11-10 10:12:30",false,"---\nname: dnanexus-integration\ndescription: \"DNAnexus cloud genomics platform. Build apps\u002Fapplets, manage data (upload\u002Fdownload), dxpy Python SDK, run workflows, FASTQ\u002FBAM\u002FVCF, for genomics pipeline development and execution.\"\n---\n\n# DNAnexus Integration\n\n## Overview\n\nDNAnexus is a cloud platform for biomedical data analysis and genomics. Build and deploy apps\u002Fapplets, manage data objects, run workflows, and use the dxpy Python SDK for genomics pipeline development and execution.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Creating, building, or modifying DNAnexus apps\u002Fapplets\n- Uploading, downloading, searching, or organizing files and records\n- Running analyses, monitoring jobs, creating workflows\n- Writing scripts using dxpy to interact with the platform\n- Setting up dxapp.json, managing dependencies, using Docker\n- Processing FASTQ, BAM, VCF, or other bioinformatics files\n- Managing projects, permissions, or platform resources\n\n## Core Capabilities\n\nThe skill is organized into five main areas, each with detailed reference documentation:\n\n### 1. App Development\n\n**Purpose**: Create executable programs (apps\u002Fapplets) that run on the DNAnexus platform.\n\n**Key Operations**:\n- Generate app skeleton with `dx-app-wizard`\n- Write Python or Bash apps with proper entry points\n- Handle input\u002Foutput data objects\n- Deploy with `dx build` or `dx build --app`\n- Test apps on the platform\n\n**Common Use Cases**:\n- Bioinformatics pipelines (alignment, variant calling)\n- Data processing workflows\n- Quality control and filtering\n- Format conversion tools\n\n**Reference**: See `references\u002Fapp-development.md` for:\n- Complete app structure and patterns\n- Python entry point decorators\n- Input\u002Foutput handling with dxpy\n- Development best practices\n- Common issues and solutions\n\n### 2. Data Operations\n\n**Purpose**: Manage files, records, and other data objects on the platform.\n\n**Key Operations**:\n- Upload\u002Fdownload files with `dxpy.upload_local_file()` and `dxpy.download_dxfile()`\n- Create and manage records with metadata\n- Search for data objects by name, properties, or type\n- Clone data between projects\n- Manage project folders and permissions\n\n**Common Use Cases**:\n- Uploading sequencing data (FASTQ files)\n- Organizing analysis results\n- Searching for specific samples or experiments\n- Backing up data across projects\n- Managing reference genomes and annotations\n\n**Reference**: See `references\u002Fdata-operations.md` for:\n- Complete file and record operations\n- Data object lifecycle (open\u002Fclosed states)\n- Search and discovery patterns\n- Project management\n- Batch operations\n\n### 3. Job Execution\n\n**Purpose**: Run analyses, monitor execution, and orchestrate workflows.\n\n**Key Operations**:\n- Launch jobs with `applet.run()` or `app.run()`\n- Monitor job status and logs\n- Create subjobs for parallel processing\n- Build and run multi-step workflows\n- Chain jobs with output references\n\n**Common Use Cases**:\n- Running genomics analyses on sequencing data\n- Parallel processing of multiple samples\n- Multi-step analysis pipelines\n- Monitoring long-running computations\n- Debugging failed jobs\n\n**Reference**: See `references\u002Fjob-execution.md` for:\n- Complete job lifecycle and states\n- Workflow creation and orchestration\n- Parallel execution patterns\n- Job monitoring and debugging\n- Resource management\n\n### 4. Python SDK (dxpy)\n\n**Purpose**: Programmatic access to DNAnexus platform through Python.\n\n**Key Operations**:\n- Work with data object handlers (DXFile, DXRecord, DXApplet, etc.)\n- Use high-level functions for common tasks\n- Make direct API calls for advanced operations\n- Create links and references between objects\n- Search and discover platform resources\n\n**Common Use Cases**:\n- Automation scripts for data management\n- Custom analysis pipelines\n- Batch processing workflows\n- Integration with external tools\n- Data migration and organization\n\n**Reference**: See `references\u002Fpython-sdk.md` for:\n- Complete dxpy class reference\n- High-level utility functions\n- API method documentation\n- Error handling patterns\n- Common code patterns\n\n### 5. Configuration and Dependencies\n\n**Purpose**: Configure app metadata and manage dependencies.\n\n**Key Operations**:\n- Write dxapp.json with inputs, outputs, and run specs\n- Install system packages (execDepends)\n- Bundle custom tools and resources\n- Use assets for shared dependencies\n- Integrate Docker containers\n- Configure instance types and timeouts\n\n**Common Use Cases**:\n- Defining app input\u002Foutput specifications\n- Installing bioinformatics tools (samtools, bwa, etc.)\n- Managing Python package dependencies\n- Using Docker images for complex environments\n- Selecting computational resources\n\n**Reference**: See `references\u002Fconfiguration.md` for:\n- Complete dxapp.json specification\n- Dependency management strategies\n- Docker integration patterns\n- Regional and resource configuration\n- Example configurations\n\n## Quick Start Examples\n\n### Upload and Analyze Data\n\n```python\nimport dxpy\n\n# Upload input file\ninput_file = dxpy.upload_local_file(\"sample.fastq\", project=\"project-xxxx\")\n\n# Run analysis\njob = dxpy.DXApplet(\"applet-xxxx\").run({\n    \"reads\": dxpy.dxlink(input_file.get_id())\n})\n\n# Wait for completion\njob.wait_on_done()\n\n# Download results\noutput_id = job.describe()[\"output\"][\"aligned_reads\"][\"$dnanexus_link\"]\ndxpy.download_dxfile(output_id, \"aligned.bam\")\n```\n\n### Search and Download Files\n\n```python\nimport dxpy\n\n# Find BAM files from a specific experiment\nfiles = dxpy.find_data_objects(\n    classname=\"file\",\n    name=\"*.bam\",\n    properties={\"experiment\": \"exp001\"},\n    project=\"project-xxxx\"\n)\n\n# Download each file\nfor file_result in files:\n    file_obj = dxpy.DXFile(file_result[\"id\"])\n    filename = file_obj.describe()[\"name\"]\n    dxpy.download_dxfile(file_result[\"id\"], filename)\n```\n\n### Create Simple App\n\n```python\n# src\u002Fmy-app.py\nimport dxpy\nimport subprocess\n\n@dxpy.entry_point('main')\ndef main(input_file, quality_threshold=30):\n    # Download input\n    dxpy.download_dxfile(input_file[\"$dnanexus_link\"], \"input.fastq\")\n\n    # Process\n    subprocess.check_call([\n        \"quality_filter\",\n        \"--input\", \"input.fastq\",\n        \"--output\", \"filtered.fastq\",\n        \"--threshold\", str(quality_threshold)\n    ])\n\n    # Upload output\n    output_file = dxpy.upload_local_file(\"filtered.fastq\")\n\n    return {\n        \"filtered_reads\": dxpy.dxlink(output_file)\n    }\n\ndxpy.run()\n```\n\n## Workflow Decision Tree\n\nWhen working with DNAnexus, follow this decision tree:\n\n1. **Need to create a new executable?**\n   - Yes → Use **App Development** (references\u002Fapp-development.md)\n   - No → Continue to step 2\n\n2. **Need to manage files or data?**\n   - Yes → Use **Data Operations** (references\u002Fdata-operations.md)\n   - No → Continue to step 3\n\n3. **Need to run an analysis or workflow?**\n   - Yes → Use **Job Execution** (references\u002Fjob-execution.md)\n   - No → Continue to step 4\n\n4. **Writing Python scripts for automation?**\n   - Yes → Use **Python SDK** (references\u002Fpython-sdk.md)\n   - No → Continue to step 5\n\n5. **Configuring app settings or dependencies?**\n   - Yes → Use **Configuration** (references\u002Fconfiguration.md)\n\nOften you'll need multiple capabilities together (e.g., app development + configuration, or data operations + job execution).\n\n## Installation and Authentication\n\n### Install dxpy\n\n```bash\nuv pip install dxpy\n```\n\n### Login to DNAnexus\n\n```bash\ndx login\n```\n\nThis authenticates your session and sets up access to projects and data.\n\n### Verify Installation\n\n```bash\ndx --version\ndx whoami\n```\n\n## Common Patterns\n\n### Pattern 1: Batch Processing\n\nProcess multiple files with the same analysis:\n\n```python\n# Find all FASTQ files\nfiles = dxpy.find_data_objects(\n    classname=\"file\",\n    name=\"*.fastq\",\n    project=\"project-xxxx\"\n)\n\n# Launch parallel jobs\njobs = []\nfor file_result in files:\n    job = dxpy.DXApplet(\"applet-xxxx\").run({\n        \"input\": dxpy.dxlink(file_result[\"id\"])\n    })\n    jobs.append(job)\n\n# Wait for all completions\nfor job in jobs:\n    job.wait_on_done()\n```\n\n### Pattern 2: Multi-Step Pipeline\n\nChain multiple analyses together:\n\n```python\n# Step 1: Quality control\nqc_job = qc_applet.run({\"reads\": input_file})\n\n# Step 2: Alignment (uses QC output)\nalign_job = align_applet.run({\n    \"reads\": qc_job.get_output_ref(\"filtered_reads\")\n})\n\n# Step 3: Variant calling (uses alignment output)\nvariant_job = variant_applet.run({\n    \"bam\": align_job.get_output_ref(\"aligned_bam\")\n})\n```\n\n### Pattern 3: Data Organization\n\nOrganize analysis results systematically:\n\n```python\n# Create organized folder structure\ndxpy.api.project_new_folder(\n    \"project-xxxx\",\n    {\"folder\": \"\u002Fexperiments\u002Fexp001\u002Fresults\", \"parents\": True}\n)\n\n# Upload with metadata\nresult_file = dxpy.upload_local_file(\n    \"results.txt\",\n    project=\"project-xxxx\",\n    folder=\"\u002Fexperiments\u002Fexp001\u002Fresults\",\n    properties={\n        \"experiment\": \"exp001\",\n        \"sample\": \"sample1\",\n        \"analysis_date\": \"2025-10-20\"\n    },\n    tags=[\"validated\", \"published\"]\n)\n```\n\n## Best Practices\n\n1. **Error Handling**: Always wrap API calls in try-except blocks\n2. **Resource Management**: Choose appropriate instance types for workloads\n3. **Data Organization**: Use consistent folder structures and metadata\n4. **Cost Optimization**: Archive old data, use appropriate storage classes\n5. **Documentation**: Include clear descriptions in dxapp.json\n6. **Testing**: Test apps with various input types before production use\n7. **Version Control**: Use semantic versioning for apps\n8. **Security**: Never hardcode credentials in source code\n9. **Logging**: Include informative log messages for debugging\n10. **Cleanup**: Remove temporary files and failed jobs\n\n## Resources\n\nThis skill includes detailed reference documentation:\n\n### references\u002F\n\n- **app-development.md** - Complete guide to building and deploying apps\u002Fapplets\n- **data-operations.md** - File management, records, search, and project operations\n- **job-execution.md** - Running jobs, workflows, monitoring, and parallel processing\n- **python-sdk.md** - Comprehensive dxpy library reference with all classes and functions\n- **configuration.md** - dxapp.json specification and dependency management\n\nLoad these references when you need detailed information about specific operations or when working on complex tasks.\n\n## Getting Help\n\n- Official documentation: https:\u002F\u002Fdocumentation.dnanexus.com\u002F\n- API reference: http:\u002F\u002Fautodoc.dnanexus.com\u002F\n- GitHub repository: https:\u002F\u002Fgithub.com\u002Fdnanexus\u002Fdx-toolkit\n- Support: support@dnanexus.com\n","# DNAnexus Integration\n\n## Overview\n\nDNAnexus is a cloud platform for biomedical data analysis and genomics. Build and deploy apps\u002Fapplets, manage data objects, run workflows, and use the dxpy Python SDK for genomics pipeline development and execution.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Creating, building, or modifying DNAnexus apps\u002Fapplets\n- Uploading, downloading, searching, or organizing files and records\n- Running analyses, monitoring jobs, creating workflows\n- Writing scripts using dxpy to interact with the platform\n- Setting up dxapp.json, managing dependencies, using Docker\n- Processing FASTQ, BAM, VCF, or other bioinformatics files\n- Managing projects, permissions, or platform resources\n\n## Core Capabilities\n\nThe skill is organized into five main areas, each with detailed reference documentation:\n\n### 1. App Development\n\n**Purpose**: Create executable programs (apps\u002Fapplets) that run on the DNAnexus platform.\n\n**Key Operations**:\n- Generate app skeleton with `dx-app-wizard`\n- Write Python or Bash apps with proper entry points\n- Handle input\u002Foutput data objects\n- Deploy with `dx build` or `dx build --app`\n- Test apps on the platform\n\n**Common Use Cases**:\n- Bioinformatics pipelines (alignment, variant calling)\n- Data processing workflows\n- Quality control and filtering\n- Format conversion tools\n\n**Reference**: See `references\u002Fapp-development.md` for:\n- Complete app structure and patterns\n- Python entry point decorators\n- Input\u002Foutput handling with dxpy\n- Development best practices\n- Common issues and solutions\n\n### 2. Data Operations\n\n**Purpose**: Manage files, records, and other data objects on the platform.\n\n**Key Operations**:\n- Upload\u002Fdownload files with `dxpy.upload_local_file()` and `dxpy.download_dxfile()`\n- Create and manage records with metadata\n- Search for data objects by name, properties, or type\n- Clone data between projects\n- Manage project folders and permissions\n\n**Common Use Cases**:\n- Uploading sequencing data (FASTQ files)\n- Organizing analysis results\n- Searching for specific samples or experiments\n- Backing up data across projects\n- Managing reference genomes and annotations\n\n**Reference**: See `references\u002Fdata-operations.md` for:\n- Complete file and record operations\n- Data object lifecycle (open\u002Fclosed states)\n- Search and discovery patterns\n- Project management\n- Batch operations\n\n### 3. Job Execution\n\n**Purpose**: Run analyses, monitor execution, and orchestrate workflows.\n\n**Key Operations**:\n- Launch jobs with `applet.run()` or `app.run()`\n- Monitor job status and logs\n- Create subjobs for parallel processing\n- Build and run multi-step workflows\n- Chain jobs with output references\n\n**Common Use Cases**:\n- Running genomics analyses on sequencing data\n- Parallel processing of multiple samples\n- Multi-step analysis pipelines\n- Monitoring long-running computations\n- Debugging failed jobs\n\n**Reference**: See `references\u002Fjob-execution.md` for:\n- Complete job lifecycle and states\n- Workflow creation and orchestration\n- Parallel execution patterns\n- Job monitoring and debugging\n- Resource management\n\n### 4. Python SDK (dxpy)\n\n**Purpose**: Programmatic access to DNAnexus platform through Python.\n\n**Key Operations**:\n- Work with data object handlers (DXFile, DXRecord, DXApplet, etc.)\n- Use high-level functions for common tasks\n- Make direct API calls for advanced operations\n- Create links and references between objects\n- Search and discover platform resources\n\n**Common Use Cases**:\n- Automation scripts for data management\n- Custom analysis pipelines\n- Batch processing workflows\n- Integration with external tools\n- Data migration and organization\n\n**Reference**: See `references\u002Fpython-sdk.md` for:\n- Complete dxpy class reference\n- High-level utility functions\n- API method documentation\n- Error handling patterns\n- Common code patterns\n\n### 5. Configuration and Dependencies\n\n**Purpose**: Configure app metadata and manage dependencies.\n\n**Key Operations**:\n- Write dxapp.json with inputs, outputs, and run specs\n- Install system packages (execDepends)\n- Bundle custom tools and resources\n- Use assets for shared dependencies\n- Integrate Docker containers\n- Configure instance types and timeouts\n\n**Common Use Cases**:\n- Defining app input\u002Foutput specifications\n- Installing bioinformatics tools (samtools, bwa, etc.)\n- Managing Python package dependencies\n- Using Docker images for complex environments\n- Selecting computational resources\n\n**Reference**: See `references\u002Fconfiguration.md` for:\n- Complete dxapp.json specification\n- Dependency management strategies\n- Docker integration patterns\n- Regional and resource configuration\n- Example configurations\n\n## Quick Start Examples\n\n### Upload and Analyze Data\n\n```python\nimport dxpy\n\n# Upload input file\ninput_file = dxpy.upload_local_file(\"sample.fastq\", project=\"project-xxxx\")\n\n# Run analysis\njob = dxpy.DXApplet(\"applet-xxxx\").run({\n    \"reads\": dxpy.dxlink(input_file.get_id())\n})\n\n# Wait for completion\njob.wait_on_done()\n\n# Download results\noutput_id = job.describe()[\"output\"][\"aligned_reads\"][\"$dnanexus_link\"]\ndxpy.download_dxfile(output_id, \"aligned.bam\")\n```\n\n### Search and Download Files\n\n```python\nimport dxpy\n\n# Find BAM files from a specific experiment\nfiles = dxpy.find_data_objects(\n    classname=\"file\",\n    name=\"*.bam\",\n    properties={\"experiment\": \"exp001\"},\n    project=\"project-xxxx\"\n)\n\n# Download each file\nfor file_result in files:\n    file_obj = dxpy.DXFile(file_result[\"id\"])\n    filename = file_obj.describe()[\"name\"]\n    dxpy.download_dxfile(file_result[\"id\"], filename)\n```\n\n### Create Simple App\n\n```python\n# src\u002Fmy-app.py\nimport dxpy\nimport subprocess\n\n@dxpy.entry_point('main')\ndef main(input_file, quality_threshold=30):\n    # Download input\n    dxpy.download_dxfile(input_file[\"$dnanexus_link\"], \"input.fastq\")\n\n    # Process\n    subprocess.check_call([\n        \"quality_filter\",\n        \"--input\", \"input.fastq\",\n        \"--output\", \"filtered.fastq\",\n        \"--threshold\", str(quality_threshold)\n    ])\n\n    # Upload output\n    output_file = dxpy.upload_local_file(\"filtered.fastq\")\n\n    return {\n        \"filtered_reads\": dxpy.dxlink(output_file)\n    }\n\ndxpy.run()\n```\n\n## Workflow Decision Tree\n\nWhen working with DNAnexus, follow this decision tree:\n\n1. **Need to create a new executable?**\n   - Yes → Use **App Development** (references\u002Fapp-development.md)\n   - No → Continue to step 2\n\n2. **Need to manage files or data?**\n   - Yes → Use **Data Operations** (references\u002Fdata-operations.md)\n   - No → Continue to step 3\n\n3. **Need to run an analysis or workflow?**\n   - Yes → Use **Job Execution** (references\u002Fjob-execution.md)\n   - No → Continue to step 4\n\n4. **Writing Python scripts for automation?**\n   - Yes → Use **Python SDK** (references\u002Fpython-sdk.md)\n   - No → Continue to step 5\n\n5. **Configuring app settings or dependencies?**\n   - Yes → Use **Configuration** (references\u002Fconfiguration.md)\n\nOften you'll need multiple capabilities together (e.g., app development + configuration, or data operations + job execution).\n\n## Installation and Authentication\n\n### Install dxpy\n\n```bash\nuv pip install dxpy\n```\n\n### Login to DNAnexus\n\n```bash\ndx login\n```\n\nThis authenticates your session and sets up access to projects and data.\n\n### Verify Installation\n\n```bash\ndx --version\ndx whoami\n```\n\n## Common Patterns\n\n### Pattern 1: Batch Processing\n\nProcess multiple files with the same analysis:\n\n```python\n# Find all FASTQ files\nfiles = dxpy.find_data_objects(\n    classname=\"file\",\n    name=\"*.fastq\",\n    project=\"project-xxxx\"\n)\n\n# Launch parallel jobs\njobs = []\nfor file_result in files:\n    job = dxpy.DXApplet(\"applet-xxxx\").run({\n        \"input\": dxpy.dxlink(file_result[\"id\"])\n    })\n    jobs.append(job)\n\n# Wait for all completions\nfor job in jobs:\n    job.wait_on_done()\n```\n\n### Pattern 2: Multi-Step Pipeline\n\nChain multiple analyses together:\n\n```python\n# Step 1: Quality control\nqc_job = qc_applet.run({\"reads\": input_file})\n\n# Step 2: Alignment (uses QC output)\nalign_job = align_applet.run({\n    \"reads\": qc_job.get_output_ref(\"filtered_reads\")\n})\n\n# Step 3: Variant calling (uses alignment output)\nvariant_job = variant_applet.run({\n    \"bam\": align_job.get_output_ref(\"aligned_bam\")\n})\n```\n\n### Pattern 3: Data Organization\n\nOrganize analysis results systematically:\n\n```python\n# Create organized folder structure\ndxpy.api.project_new_folder(\n    \"project-xxxx\",\n    {\"folder\": \"\u002Fexperiments\u002Fexp001\u002Fresults\", \"parents\": True}\n)\n\n# Upload with metadata\nresult_file = dxpy.upload_local_file(\n    \"results.txt\",\n    project=\"project-xxxx\",\n    folder=\"\u002Fexperiments\u002Fexp001\u002Fresults\",\n    properties={\n        \"experiment\": \"exp001\",\n        \"sample\": \"sample1\",\n        \"analysis_date\": \"2025-10-20\"\n    },\n    tags=[\"validated\", \"published\"]\n)\n```\n\n## Best Practices\n\n1. **Error Handling**: Always wrap API calls in try-except blocks\n2. **Resource Management**: Choose appropriate instance types for workloads\n3. **Data Organization**: Use consistent folder structures and metadata\n4. **Cost Optimization**: Archive old data, use appropriate storage classes\n5. **Documentation**: Include clear descriptions in dxapp.json\n6. **Testing**: Test apps with various input types before production use\n7. **Version Control**: Use semantic versioning for apps\n8. **Security**: Never hardcode credentials in source code\n9. **Logging**: Include informative log messages for debugging\n10. **Cleanup**: Remove temporary files and failed jobs\n\n## Resources\n\nThis skill includes detailed reference documentation:\n\n### references\u002F\n\n- **app-development.md** - Complete guide to building and deploying apps\u002Fapplets\n- **data-operations.md** - File management, records, search, and project operations\n- **job-execution.md** - Running jobs, workflows, monitoring, and parallel processing\n- **python-sdk.md** - Comprehensive dxpy library reference with all classes and functions\n- **configuration.md** - dxapp.json specification and dependency management\n\nLoad these references when you need detailed information about specific operations or when working on complex tasks.\n\n## Getting Help\n\n- Official documentation: https:\u002F\u002Fdocumentation.dnanexus.com\u002F\n- API reference: http:\u002F\u002Fautodoc.dnanexus.com\u002F\n- GitHub repository: https:\u002F\u002Fgithub.com\u002Fdnanexus\u002Fdx-toolkit\n- Support: support@dnanexus.com\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fdnanexus-integration",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":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add davila7\u002Fclaude-code-templates --skill dnanexus-integration",{"tool":67,"command":68},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill dnanexus-integration",{"tool":70,"command":71},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill dnanexus-integration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fdnanexus-integration\u002FSKILL.md",true,[75,81,85,89,93],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fapp-development.md","REFERENCE","参考文档",5291,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fdnanexus-integration\u002Freferences\u002Fapp-development.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fconfiguration.md",13172,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fdnanexus-integration\u002Freferences\u002Fconfiguration.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fdata-operations.md",8120,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fdnanexus-integration\u002Freferences\u002Fdata-operations.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fjob-execution.md",8766,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fdnanexus-integration\u002Freferences\u002Fjob-execution.md",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fpython-sdk.md",9776,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fdnanexus-integration\u002Freferences\u002Fpython-sdk.md",[98,125,152,185,220,244],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":46},"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",[104],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,108,109,110,26,111,112,113,114,115,116,117,118,119,120,121,122,123,124],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":132,"publishedAt":46},"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",[131],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[133,134,135,136,137,138,139,140,141,142,143,114,144,145,146,147,148,149,150,151],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":167,"publishedAt":46},"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",[158,161,162],{"categoryNo":159,"categoryName":160,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":163,"categoryName":164,"taxonomyType":165,"taxonomyTypeDesc":166},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[168,169,170,171,172,173,174,26,175,176,177,178,179,180,181,113,182,183,114,184],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":189,"licenseFileUrl":190,"sourceHtmlUrl":191,"categories":192,"keywords":196,"publishedAt":46},"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",[193],{"categoryNo":194,"categoryName":195,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,26,219],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":189,"licenseFileUrl":224,"sourceHtmlUrl":225,"categories":226,"keywords":231,"publishedAt":46},"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",[227,230],{"categoryNo":228,"categoryName":229,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":194,"categoryName":195,"taxonomyType":21,"taxonomyTypeDesc":22},[232,233,234,235,236,198,237,207,208,238,239,240,241,26,242,116,243],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":245,"name":246,"nameZh":6,"description":247,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":189,"licenseFileUrl":248,"sourceHtmlUrl":249,"categories":250,"keywords":258,"publishedAt":46},"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",[251,254,255],{"categoryNo":252,"categoryName":253,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":256,"categoryName":257,"taxonomyType":165,"taxonomyTypeDesc":166},"01JBSEEDCAT000000000000036","内容创作者",[259,260,261,262,42,263,39,264,200,265,210,144,266,267,268,269,270,180,271,114,272,273,274,275,276,122,277],"discernment nudge","nudge","interpretation","help","reasoning","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]