[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73A2M9J0TCGY60V13HWR716":3,"skill-same:01M73A2M9J0TCGY60V13HWR716":67},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M73A2M9J0TCGY60V13HWR716","pysam",null,"Genomic file toolkit. Read\u002Fwrite SAM\u002FBAM\u002FCRAM alignments, VCF\u002FBCF variants, FASTA\u002FFASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.","qhjqhj00\u002Fresearch-skills-pool","qhjqhj00","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29684092?v=4","01M72AE0ZGXVM5C57N512DGQG8","Tommy Chien","01M72AE107ESJMHT7QC5SXX144",3,"MIT","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002FK-Dense-AI--scientific-agent-skills--scientific-skills__pysam\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: pysam\ndescription: Genomic file toolkit. Read\u002Fwrite SAM\u002FBAM\u002FCRAM alignments, VCF\u002FBCF variants, FASTA\u002FFASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.\nlicense: MIT license\nmetadata:\n    skill-author: K-Dense Inc.\n---\n\n# Pysam\n\n## Overview\n\nPysam is a Python module for reading, manipulating, and writing genomic datasets. Read\u002Fwrite SAM\u002FBAM\u002FCRAM alignment files, VCF\u002FBCF variant files, and FASTA\u002FFASTQ sequences with a Pythonic interface to htslib. Query tabix-indexed files, perform pileup analysis for coverage, and execute samtools\u002Fbcftools commands.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Working with sequencing alignment files (BAM\u002FCRAM)\n- Analyzing genetic variants (VCF\u002FBCF)\n- Extracting reference sequences or gene regions\n- Processing raw sequencing data (FASTQ)\n- Calculating coverage or read depth\n- Implementing bioinformatics analysis pipelines\n- Quality control of sequencing data\n- Variant calling and annotation workflows\n\n## Quick Start\n\n### Installation\n```bash\nuv pip install pysam\n```\n\n### Basic Examples\n\n**Read alignment file:**\n```python\nimport pysam\n\n# Open BAM file and fetch reads in region\nsamfile = pysam.AlignmentFile(\"example.bam\", \"rb\")\nfor read in samfile.fetch(\"chr1\", 1000, 2000):\n    print(f\"{read.query_name}: {read.reference_start}\")\nsamfile.close()\n```\n\n**Read variant file:**\n```python\n# Open VCF file and iterate variants\nvcf = pysam.VariantFile(\"variants.vcf\")\nfor variant in vcf:\n    print(f\"{variant.chrom}:{variant.pos} {variant.ref}>{variant.alts}\")\nvcf.close()\n```\n\n**Query reference sequence:**\n```python\n# Open FASTA and extract sequence\nfasta = pysam.FastaFile(\"reference.fasta\")\nsequence = fasta.fetch(\"chr1\", 1000, 2000)\nprint(sequence)\nfasta.close()\n```\n\n## Core Capabilities\n\n### 1. Alignment File Operations (SAM\u002FBAM\u002FCRAM)\n\nUse the `AlignmentFile` class to work with aligned sequencing reads. This is appropriate for analyzing mapping results, calculating coverage, extracting reads, or quality control.\n\n**Common operations:**\n- Open and read BAM\u002FSAM\u002FCRAM files\n- Fetch reads from specific genomic regions\n- Filter reads by mapping quality, flags, or other criteria\n- Write filtered or modified alignments\n- Calculate coverage statistics\n- Perform pileup analysis (base-by-base coverage)\n- Access read sequences, quality scores, and alignment information\n\n**Reference:** See `references\u002Falignment_files.md` for detailed documentation on:\n- Opening and reading alignment files\n- AlignedSegment attributes and methods\n- Region-based fetching with `fetch()`\n- Pileup analysis for coverage\n- Writing and creating BAM files\n- Coordinate systems and indexing\n- Performance optimization tips\n\n### 2. Variant File Operations (VCF\u002FBCF)\n\nUse the `VariantFile` class to work with genetic variants from variant calling pipelines. This is appropriate for variant analysis, filtering, annotation, or population genetics.\n\n**Common operations:**\n- Read and write VCF\u002FBCF files\n- Query variants in specific regions\n- Access variant information (position, alleles, quality)\n- Extract genotype data for samples\n- Filter variants by quality, allele frequency, or other criteria\n- Annotate variants with additional information\n- Subset samples or regions\n\n**Reference:** See `references\u002Fvariant_files.md` for detailed documentation on:\n- Opening and reading variant files\n- VariantRecord attributes and methods\n- Accessing INFO and FORMAT fields\n- Working with genotypes and samples\n- Creating and writing VCF files\n- Filtering and subsetting variants\n- Multi-sample VCF operations\n\n### 3. Sequence File Operations (FASTA\u002FFASTQ)\n\nUse `FastaFile` for random access to reference sequences and `FastxFile` for reading raw sequencing data. This is appropriate for extracting gene sequences, validating variants against reference, or processing raw reads.\n\n**Common operations:**\n- Query reference sequences by genomic coordinates\n- Extract sequences for genes or regions of interest\n- Read FASTQ files with quality scores\n- Validate variant reference alleles\n- Calculate sequence statistics\n- Filter reads by quality or length\n- Convert between FASTA and FASTQ formats\n\n**Reference:** See `references\u002Fsequence_files.md` for detailed documentation on:\n- FASTA file access and indexing\n- Extracting sequences by region\n- Handling reverse complement for genes\n- Reading FASTQ files sequentially\n- Quality score conversion and filtering\n- Working with tabix-indexed files (BED, GTF, GFF)\n- Common sequence processing patterns\n\n### 4. Integrated Bioinformatics Workflows\n\nPysam excels at integrating multiple file types for comprehensive genomic analyses. Common workflows combine alignment files, variant files, and reference sequences.\n\n**Common workflows:**\n- Calculate coverage statistics for specific regions\n- Validate variants against aligned reads\n- Annotate variants with coverage information\n- Extract sequences around variant positions\n- Filter alignments or variants based on multiple criteria\n- Generate coverage tracks for visualization\n- Quality control across multiple data types\n\n**Reference:** See `references\u002Fcommon_workflows.md` for detailed examples of:\n- Quality control workflows (BAM statistics, reference consistency)\n- Coverage analysis (per-base coverage, low coverage detection)\n- Variant analysis (annotation, filtering by read support)\n- Sequence extraction (variant contexts, gene sequences)\n- Read filtering and subsetting\n- Integration patterns (BAM+VCF, VCF+BED, etc.)\n- Performance optimization for complex workflows\n\n## Key Concepts\n\n### Coordinate Systems\n\n**Critical:** Pysam uses **0-based, half-open** coordinates (Python convention):\n- Start positions are 0-based (first base is position 0)\n- End positions are exclusive (not included in the range)\n- Region 1000-2000 includes bases 1000-1999 (1000 bases total)\n\n**Exception:** Region strings in `fetch()` follow samtools convention (1-based):\n```python\nsamfile.fetch(\"chr1\", 999, 2000)      # 0-based: positions 999-1999\nsamfile.fetch(\"chr1:1000-2000\")       # 1-based string: positions 1000-2000\n```\n\n**VCF files:** Use 1-based coordinates in the file format, but `VariantRecord.start` is 0-based.\n\n### Indexing Requirements\n\nRandom access to specific genomic regions requires index files:\n- **BAM files**: Require `.bai` index (create with `pysam.index()`)\n- **CRAM files**: Require `.crai` index\n- **FASTA files**: Require `.fai` index (create with `pysam.faidx()`)\n- **VCF.gz files**: Require `.tbi` tabix index (create with `pysam.tabix_index()`)\n- **BCF files**: Require `.csi` index\n\nWithout an index, use `fetch(until_eof=True)` for sequential reading.\n\n### File Modes\n\nSpecify format when opening files:\n- `\"rb\"` - Read BAM (binary)\n- `\"r\"` - Read SAM (text)\n- `\"rc\"` - Read CRAM\n- `\"wb\"` - Write BAM\n- `\"w\"` - Write SAM\n- `\"wc\"` - Write CRAM\n\n### Performance Considerations\n\n1. **Always use indexed files** for random access operations\n2. **Use `pileup()` for column-wise analysis** instead of repeated fetch operations\n3. **Use `count()` for counting** instead of iterating and counting manually\n4. **Process regions in parallel** when analyzing independent genomic regions\n5. **Close files explicitly** to free resources\n6. **Use `until_eof=True`** for sequential processing without index\n7. **Avoid multiple iterators** unless necessary (use `multiple_iterators=True` if needed)\n\n## Common Pitfalls\n\n1. **Coordinate confusion:** Remember 0-based vs 1-based systems in different contexts\n2. **Missing indices:** Many operations require index files—create them first\n3. **Partial overlaps:** `fetch()` returns reads overlapping region boundaries, not just those fully contained\n4. **Iterator scope:** Keep pileup iterator references alive to avoid \"PileupProxy accessed after iterator finished\" errors\n5. **Quality score editing:** Cannot modify `query_qualities` in place after changing `query_sequence`—create a copy first\n6. **Stream limitations:** Only stdin\u002Fstdout are supported for streaming, not arbitrary Python file objects\n7. **Thread safety:** While GIL is released during I\u002FO, comprehensive thread-safety hasn't been fully validated\n\n## Command-Line Tools\n\nPysam provides access to samtools and bcftools commands:\n\n```python\n# Sort BAM file\npysam.samtools.sort(\"-o\", \"sorted.bam\", \"input.bam\")\n\n# Index BAM\npysam.samtools.index(\"sorted.bam\")\n\n# View specific region\npysam.samtools.view(\"-b\", \"-o\", \"region.bam\", \"input.bam\", \"chr1:1000-2000\")\n\n# BCF tools\npysam.bcftools.view(\"-O\", \"z\", \"-o\", \"output.vcf.gz\", \"input.vcf\")\n```\n\n**Error handling:**\n```python\ntry:\n    pysam.samtools.sort(\"-o\", \"output.bam\", \"input.bam\")\nexcept pysam.SamtoolsError as e:\n    print(f\"Error: {e}\")\n```\n\n## Resources\n\n### references\u002F\n\nDetailed documentation for each major capability:\n\n- **alignment_files.md** - Complete guide to SAM\u002FBAM\u002FCRAM operations, including AlignmentFile class, AlignedSegment attributes, fetch operations, pileup analysis, and writing alignments\n\n- **variant_files.md** - Complete guide to VCF\u002FBCF operations, including VariantFile class, VariantRecord attributes, genotype handling, INFO\u002FFORMAT fields, and multi-sample operations\n\n- **sequence_files.md** - Complete guide to FASTA\u002FFASTQ operations, including FastaFile and FastxFile classes, sequence extraction, quality score handling, and tabix-indexed file access\n\n- **common_workflows.md** - Practical examples of integrated bioinformatics workflows combining multiple file types, including quality control, coverage analysis, variant validation, and sequence extraction\n\n## Getting Help\n\nFor detailed information on specific operations, refer to the appropriate reference document:\n\n- Working with BAM files or calculating coverage → `alignment_files.md`\n- Analyzing variants or genotypes → `variant_files.md`\n- Extracting sequences or processing FASTQ → `sequence_files.md`\n- Complex workflows integrating multiple file types → `common_workflows.md`\n\nOfficial documentation: https:\u002F\u002Fpysam.readthedocs.io\u002F\n\n","# Pysam\n\n## Overview\n\nPysam is a Python module for reading, manipulating, and writing genomic datasets. Read\u002Fwrite SAM\u002FBAM\u002FCRAM alignment files, VCF\u002FBCF variant files, and FASTA\u002FFASTQ sequences with a Pythonic interface to htslib. Query tabix-indexed files, perform pileup analysis for coverage, and execute samtools\u002Fbcftools commands.\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Working with sequencing alignment files (BAM\u002FCRAM)\n- Analyzing genetic variants (VCF\u002FBCF)\n- Extracting reference sequences or gene regions\n- Processing raw sequencing data (FASTQ)\n- Calculating coverage or read depth\n- Implementing bioinformatics analysis pipelines\n- Quality control of sequencing data\n- Variant calling and annotation workflows\n\n## Quick Start\n\n### Installation\n```bash\nuv pip install pysam\n```\n\n### Basic Examples\n\n**Read alignment file:**\n```python\nimport pysam\n\n# Open BAM file and fetch reads in region\nsamfile = pysam.AlignmentFile(\"example.bam\", \"rb\")\nfor read in samfile.fetch(\"chr1\", 1000, 2000):\n    print(f\"{read.query_name}: {read.reference_start}\")\nsamfile.close()\n```\n\n**Read variant file:**\n```python\n# Open VCF file and iterate variants\nvcf = pysam.VariantFile(\"variants.vcf\")\nfor variant in vcf:\n    print(f\"{variant.chrom}:{variant.pos} {variant.ref}>{variant.alts}\")\nvcf.close()\n```\n\n**Query reference sequence:**\n```python\n# Open FASTA and extract sequence\nfasta = pysam.FastaFile(\"reference.fasta\")\nsequence = fasta.fetch(\"chr1\", 1000, 2000)\nprint(sequence)\nfasta.close()\n```\n\n## Core Capabilities\n\n### 1. Alignment File Operations (SAM\u002FBAM\u002FCRAM)\n\nUse the `AlignmentFile` class to work with aligned sequencing reads. This is appropriate for analyzing mapping results, calculating coverage, extracting reads, or quality control.\n\n**Common operations:**\n- Open and read BAM\u002FSAM\u002FCRAM files\n- Fetch reads from specific genomic regions\n- Filter reads by mapping quality, flags, or other criteria\n- Write filtered or modified alignments\n- Calculate coverage statistics\n- Perform pileup analysis (base-by-base coverage)\n- Access read sequences, quality scores, and alignment information\n\n**Reference:** See `references\u002Falignment_files.md` for detailed documentation on:\n- Opening and reading alignment files\n- AlignedSegment attributes and methods\n- Region-based fetching with `fetch()`\n- Pileup analysis for coverage\n- Writing and creating BAM files\n- Coordinate systems and indexing\n- Performance optimization tips\n\n### 2. Variant File Operations (VCF\u002FBCF)\n\nUse the `VariantFile` class to work with genetic variants from variant calling pipelines. This is appropriate for variant analysis, filtering, annotation, or population genetics.\n\n**Common operations:**\n- Read and write VCF\u002FBCF files\n- Query variants in specific regions\n- Access variant information (position, alleles, quality)\n- Extract genotype data for samples\n- Filter variants by quality, allele frequency, or other criteria\n- Annotate variants with additional information\n- Subset samples or regions\n\n**Reference:** See `references\u002Fvariant_files.md` for detailed documentation on:\n- Opening and reading variant files\n- VariantRecord attributes and methods\n- Accessing INFO and FORMAT fields\n- Working with genotypes and samples\n- Creating and writing VCF files\n- Filtering and subsetting variants\n- Multi-sample VCF operations\n\n### 3. Sequence File Operations (FASTA\u002FFASTQ)\n\nUse `FastaFile` for random access to reference sequences and `FastxFile` for reading raw sequencing data. This is appropriate for extracting gene sequences, validating variants against reference, or processing raw reads.\n\n**Common operations:**\n- Query reference sequences by genomic coordinates\n- Extract sequences for genes or regions of interest\n- Read FASTQ files with quality scores\n- Validate variant reference alleles\n- Calculate sequence statistics\n- Filter reads by quality or length\n- Convert between FASTA and FASTQ formats\n\n**Reference:** See `references\u002Fsequence_files.md` for detailed documentation on:\n- FASTA file access and indexing\n- Extracting sequences by region\n- Handling reverse complement for genes\n- Reading FASTQ files sequentially\n- Quality score conversion and filtering\n- Working with tabix-indexed files (BED, GTF, GFF)\n- Common sequence processing patterns\n\n### 4. Integrated Bioinformatics Workflows\n\nPysam excels at integrating multiple file types for comprehensive genomic analyses. Common workflows combine alignment files, variant files, and reference sequences.\n\n**Common workflows:**\n- Calculate coverage statistics for specific regions\n- Validate variants against aligned reads\n- Annotate variants with coverage information\n- Extract sequences around variant positions\n- Filter alignments or variants based on multiple criteria\n- Generate coverage tracks for visualization\n- Quality control across multiple data types\n\n**Reference:** See `references\u002Fcommon_workflows.md` for detailed examples of:\n- Quality control workflows (BAM statistics, reference consistency)\n- Coverage analysis (per-base coverage, low coverage detection)\n- Variant analysis (annotation, filtering by read support)\n- Sequence extraction (variant contexts, gene sequences)\n- Read filtering and subsetting\n- Integration patterns (BAM+VCF, VCF+BED, etc.)\n- Performance optimization for complex workflows\n\n## Key Concepts\n\n### Coordinate Systems\n\n**Critical:** Pysam uses **0-based, half-open** coordinates (Python convention):\n- Start positions are 0-based (first base is position 0)\n- End positions are exclusive (not included in the range)\n- Region 1000-2000 includes bases 1000-1999 (1000 bases total)\n\n**Exception:** Region strings in `fetch()` follow samtools convention (1-based):\n```python\nsamfile.fetch(\"chr1\", 999, 2000)      # 0-based: positions 999-1999\nsamfile.fetch(\"chr1:1000-2000\")       # 1-based string: positions 1000-2000\n```\n\n**VCF files:** Use 1-based coordinates in the file format, but `VariantRecord.start` is 0-based.\n\n### Indexing Requirements\n\nRandom access to specific genomic regions requires index files:\n- **BAM files**: Require `.bai` index (create with `pysam.index()`)\n- **CRAM files**: Require `.crai` index\n- **FASTA files**: Require `.fai` index (create with `pysam.faidx()`)\n- **VCF.gz files**: Require `.tbi` tabix index (create with `pysam.tabix_index()`)\n- **BCF files**: Require `.csi` index\n\nWithout an index, use `fetch(until_eof=True)` for sequential reading.\n\n### File Modes\n\nSpecify format when opening files:\n- `\"rb\"` - Read BAM (binary)\n- `\"r\"` - Read SAM (text)\n- `\"rc\"` - Read CRAM\n- `\"wb\"` - Write BAM\n- `\"w\"` - Write SAM\n- `\"wc\"` - Write CRAM\n\n### Performance Considerations\n\n1. **Always use indexed files** for random access operations\n2. **Use `pileup()` for column-wise analysis** instead of repeated fetch operations\n3. **Use `count()` for counting** instead of iterating and counting manually\n4. **Process regions in parallel** when analyzing independent genomic regions\n5. **Close files explicitly** to free resources\n6. **Use `until_eof=True`** for sequential processing without index\n7. **Avoid multiple iterators** unless necessary (use `multiple_iterators=True` if needed)\n\n## Common Pitfalls\n\n1. **Coordinate confusion:** Remember 0-based vs 1-based systems in different contexts\n2. **Missing indices:** Many operations require index files—create them first\n3. **Partial overlaps:** `fetch()` returns reads overlapping region boundaries, not just those fully contained\n4. **Iterator scope:** Keep pileup iterator references alive to avoid \"PileupProxy accessed after iterator finished\" errors\n5. **Quality score editing:** Cannot modify `query_qualities` in place after changing `query_sequence`—create a copy first\n6. **Stream limitations:** Only stdin\u002Fstdout are supported for streaming, not arbitrary Python file objects\n7. **Thread safety:** While GIL is released during I\u002FO, comprehensive thread-safety hasn't been fully validated\n\n## Command-Line Tools\n\nPysam provides access to samtools and bcftools commands:\n\n```python\n# Sort BAM file\npysam.samtools.sort(\"-o\", \"sorted.bam\", \"input.bam\")\n\n# Index BAM\npysam.samtools.index(\"sorted.bam\")\n\n# View specific region\npysam.samtools.view(\"-b\", \"-o\", \"region.bam\", \"input.bam\", \"chr1:1000-2000\")\n\n# BCF tools\npysam.bcftools.view(\"-O\", \"z\", \"-o\", \"output.vcf.gz\", \"input.vcf\")\n```\n\n**Error handling:**\n```python\ntry:\n    pysam.samtools.sort(\"-o\", \"output.bam\", \"input.bam\")\nexcept pysam.SamtoolsError as e:\n    print(f\"Error: {e}\")\n```\n\n## Resources\n\n### references\u002F\n\nDetailed documentation for each major capability:\n\n- **alignment_files.md** - Complete guide to SAM\u002FBAM\u002FCRAM operations, including AlignmentFile class, AlignedSegment attributes, fetch operations, pileup analysis, and writing alignments\n\n- **variant_files.md** - Complete guide to VCF\u002FBCF operations, including VariantFile class, VariantRecord attributes, genotype handling, INFO\u002FFORMAT fields, and multi-sample operations\n\n- **sequence_files.md** - Complete guide to FASTA\u002FFASTQ operations, including FastaFile and FastxFile classes, sequence extraction, quality score handling, and tabix-indexed file access\n\n- **common_workflows.md** - Practical examples of integrated bioinformatics workflows combining multiple file types, including quality control, coverage analysis, variant validation, and sequence extraction\n\n## Getting Help\n\nFor detailed information on specific operations, refer to the appropriate reference document:\n\n- Working with BAM files or calculating coverage → `alignment_files.md`\n- Analyzing variants or genotypes → `variant_files.md`\n- Extracting sequences or processing FASTQ → `sequence_files.md`\n- Complex workflows integrating multiple file types → `common_workflows.md`\n\nOfficial documentation: https:\u002F\u002Fpysam.readthedocs.io\u002F\n\n",{"name":5,"license":24,"metadata":25,"description":7},"MIT license",{"skill-author":26},"K-Dense Inc.","master","c247302c836de6438d746b45670990eb71691166","skills_collected\u002FK-Dense-AI--scientific-agent-skills--scientific-skills__pysam",1,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool","https:\u002F\u002Fgithub.com\u002Fqhjqhj00","chien.io","2026-05-11 15:07:59",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add qhjqhj00\u002Fresearch-skills-pool --skill pysam",{"tool":41,"command":42},"bunx","bunx skills add qhjqhj00\u002Fresearch-skills-pool --skill pysam",{"tool":44,"command":45},"pnpm","pnpm dlx skills add qhjqhj00\u002Fresearch-skills-pool --skill pysam","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002FK-Dense-AI--scientific-agent-skills--scientific-skills__pysam\u002FSKILL.md",true,[49,55,59,63],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Falignment_files.md","REFERENCE","参考文档",8560,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002FK-Dense-AI--scientific-agent-skills--scientific-skills__pysam\u002Freferences\u002Falignment_files.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fcommon_workflows.md",15350,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002FK-Dense-AI--scientific-agent-skills--scientific-skills__pysam\u002Freferences\u002Fcommon_workflows.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fsequence_files.md",11597,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002FK-Dense-AI--scientific-agent-skills--scientific-skills__pysam\u002Freferences\u002Fsequence_files.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fvariant_files.md",9487,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002FK-Dense-AI--scientific-agent-skills--scientific-skills__pysam\u002Freferences\u002Fvariant_files.md",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M73JJB6EQPFPPVQK2Y9N67Q0","transformer-lens-interpretability","Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F130-transformer-lens\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M73JHTANRRWEE9HP98TPEHAY","wiki-vitepress","Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production build output. Use when the user wants to create a browsable website from generated wiki pages.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F126-wiki-vitepress\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M73JHJBMVFW46F1Y8K3SBF43","phoenix-observability","Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F124-phoenix\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M73JHFPA3A2806PMP42ZN86Q","frontend-ui-dark-ts","Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F123-frontend-ui-dark-ts\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M73JFVBVK57NRJS49TT2VDCT","tensorboard","Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F113-tensorboard\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":107,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M73JFF6PK6ZCN41C89J7HS2B","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F110-markdown-mermaid-writing\u002FSKILL.md",[],[]]