{
  "schemaVersion": "1.0",
  "item": {
    "slug": "bioinformatics",
    "name": "Bioinformatics",
    "source": "tencent",
    "type": "skill",
    "category": "数据分析",
    "sourceUrl": "https://clawhub.ai/ivangdavila/bioinformatics",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/bioinformatics",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/bioinformatics",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=bioinformatics",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "formats.md",
      "memory-template.md",
      "rnaseq.md",
      "setup.md",
      "tools.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/bioinformatics"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/bioinformatics",
    "agentPageUrl": "https://openagent3.xyz/skills/bioinformatics/agent",
    "manifestUrl": "https://openagent3.xyz/skills/bioinformatics/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/bioinformatics/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Setup",
        "body": "On first use, read setup.md for integration guidelines. Create ~/bioinformatics/ with user consent to store project context and preferences."
      },
      {
        "title": "When to Use",
        "body": "User needs to analyze biological sequences, run genomic pipelines, or interpret sequencing data. Agent handles sequence alignment, variant calling, expression analysis, and format conversions."
      },
      {
        "title": "Architecture",
        "body": "Memory lives in ~/bioinformatics/. See memory-template.md for structure.\n\n~/bioinformatics/\n├── memory.md         # Projects, preferences, reference genomes\n├── pipelines/        # Saved pipeline configurations\n└── results/          # Analysis outputs and logs"
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileSetup processsetup.mdMemory templatememory-template.mdFile formatsformats.mdTool commandstools.mdRNA-seq pipelinernaseq.mdVariant callingvariants.md"
      },
      {
        "title": "1. Verify Input Quality First",
        "body": "Before any analysis, check input data quality:\n\nFASTQ: Run FastQC, check per-base quality, adapter content\nBAM: Verify sorted, indexed (samtools quickcheck)\nVCF: Validate format (bcftools view -h)\n\nBad input → garbage output. Always QC first."
      },
      {
        "title": "2. Use Reference Genome Consistently",
        "body": "Track which reference is used per project:\n\nHuman: GRCh38/hg38 (prefer) or GRCh37/hg19\nMouse: GRCm39/mm39 or GRCm38/mm10\nMixing references = invalid results\n\nStore reference info in ~/bioinformatics/memory.md per project."
      },
      {
        "title": "3. Preserve Raw Data",
        "body": "NEVER modify original FASTQ/BAM files:\n\nWork on copies\nKeep originals read-only\nLog every transformation step"
      },
      {
        "title": "4. Resource Awareness",
        "body": "Bioinformatics commands can consume massive resources:\n\nCheck file sizes before operations\nUse streaming when possible (samtools view | ...)\nEstimate memory needs (BWA: ~6GB for human genome)\nWarn before operations >10 minutes"
      },
      {
        "title": "5. Reproducibility",
        "body": "Every analysis must be reproducible:\n\nLog exact tool versions (samtools --version)\nSave command parameters\nRecord input file checksums for critical analyses"
      },
      {
        "title": "Common Traps",
        "body": "Wrong chromosome naming — chr1 vs 1 causes silent failures. Check and convert with sed 's/^chr//'\nUnsorted BAM — Most tools expect sorted input. Symptoms: errors or wrong results with no warning\nIndex missing — BAM needs .bai, VCF needs .tbi. Commands fail cryptically without them\nMemory exhaustion — Large BAM operations kill the session. Stream or use --threads wisely\nStale indices — After modifying BAM/VCF, regenerate index. Old index = corrupt reads\n0-based vs 1-based coordinates — BED is 0-based, VCF/GFF is 1-based. Off-by-one bugs are common"
      },
      {
        "title": "File Formats Quick Reference",
        "body": "FormatPurposeKey ToolFASTAReference sequencessamtools faidxFASTQRaw reads + qualityseqtk, fastpSAM/BAMAligned readssamtoolsVCF/BCFVariantsbcftoolsBEDGenomic intervalsbedtoolsGFF/GTFGene annotationsgffreadBigWigCoverage tracksdeepTools"
      },
      {
        "title": "Quality Control",
        "body": "# FASTQ quality report\nfastqc sample.fastq.gz -o qc_reports/\n\n# Trim adapters + low quality\nfastp -i R1.fq.gz -I R2.fq.gz -o R1.clean.fq.gz -O R2.clean.fq.gz\n\n# BAM statistics\nsamtools flagstat aligned.bam\nsamtools stats aligned.bam > stats.txt"
      },
      {
        "title": "Alignment",
        "body": "# Index reference (once)\nbwa index reference.fa\n\n# Align paired-end reads\nbwa mem -t 8 reference.fa R1.fq.gz R2.fq.gz | \\\n  samtools sort -o aligned.bam -\n\n# Index BAM\nsamtools index aligned.bam"
      },
      {
        "title": "Variant Calling",
        "body": "# Call variants\nbcftools mpileup -Ou -f reference.fa aligned.bam | \\\n  bcftools call -mv -Oz -o variants.vcf.gz\n\n# Index VCF\nbcftools index variants.vcf.gz\n\n# Filter variants\nbcftools filter -s LowQual -e 'QUAL<20' variants.vcf.gz"
      },
      {
        "title": "Data Manipulation",
        "body": "# Extract region\nsamtools view -b aligned.bam chr1:1000000-2000000 > region.bam\n\n# Convert BAM to FASTQ\nsamtools fastq -1 R1.fq.gz -2 R2.fq.gz aligned.bam\n\n# Merge BAMs\nsamtools merge merged.bam sample1.bam sample2.bam\n\n# Subset VCF by region\nbcftools view -r chr1:1000-2000 variants.vcf.gz"
      },
      {
        "title": "Security & Privacy",
        "body": "Data access:\n\nOnly reads files user explicitly provides as input\nWrites outputs to directories user specifies\nStores preferences in ~/bioinformatics/ (with consent)\n\nData that stays local:\n\nAll sequence data processed locally\nNo external API calls for analysis\nPipeline configs in ~/bioinformatics/\n\nThis skill does NOT:\n\nUpload sequence data anywhere\nAccess files without explicit user instruction\nInfer or collect data beyond explicit inputs\nMake network requests during analysis\n\nNote: Installing tools (conda, brew) and downloading reference genomes requires internet access. These are user-initiated actions."
      },
      {
        "title": "Related Skills",
        "body": "Install with clawhub install <slug> if user confirms:\n\ndata-analysis — statistical interpretation\nstatistics — hypothesis testing\nscience — research methodology"
      },
      {
        "title": "Feedback",
        "body": "If useful: clawhub star bioinformatics\nStay updated: clawhub sync"
      }
    ],
    "body": "Setup\n\nOn first use, read setup.md for integration guidelines. Create ~/bioinformatics/ with user consent to store project context and preferences.\n\nWhen to Use\n\nUser needs to analyze biological sequences, run genomic pipelines, or interpret sequencing data. Agent handles sequence alignment, variant calling, expression analysis, and format conversions.\n\nArchitecture\n\nMemory lives in ~/bioinformatics/. See memory-template.md for structure.\n\n~/bioinformatics/\n├── memory.md         # Projects, preferences, reference genomes\n├── pipelines/        # Saved pipeline configurations\n└── results/          # Analysis outputs and logs\n\nQuick Reference\nTopic\tFile\nSetup process\tsetup.md\nMemory template\tmemory-template.md\nFile formats\tformats.md\nTool commands\ttools.md\nRNA-seq pipeline\trnaseq.md\nVariant calling\tvariants.md\nCore Rules\n1. Verify Input Quality First\n\nBefore any analysis, check input data quality:\n\nFASTQ: Run FastQC, check per-base quality, adapter content\nBAM: Verify sorted, indexed (samtools quickcheck)\nVCF: Validate format (bcftools view -h)\n\nBad input → garbage output. Always QC first.\n\n2. Use Reference Genome Consistently\n\nTrack which reference is used per project:\n\nHuman: GRCh38/hg38 (prefer) or GRCh37/hg19\nMouse: GRCm39/mm39 or GRCm38/mm10\nMixing references = invalid results\n\nStore reference info in ~/bioinformatics/memory.md per project.\n\n3. Preserve Raw Data\n\nNEVER modify original FASTQ/BAM files:\n\nWork on copies\nKeep originals read-only\nLog every transformation step\n4. Resource Awareness\n\nBioinformatics commands can consume massive resources:\n\nCheck file sizes before operations\nUse streaming when possible (samtools view | ...)\nEstimate memory needs (BWA: ~6GB for human genome)\nWarn before operations >10 minutes\n5. Reproducibility\n\nEvery analysis must be reproducible:\n\nLog exact tool versions (samtools --version)\nSave command parameters\nRecord input file checksums for critical analyses\nCommon Traps\nWrong chromosome naming — chr1 vs 1 causes silent failures. Check and convert with sed 's/^chr//'\nUnsorted BAM — Most tools expect sorted input. Symptoms: errors or wrong results with no warning\nIndex missing — BAM needs .bai, VCF needs .tbi. Commands fail cryptically without them\nMemory exhaustion — Large BAM operations kill the session. Stream or use --threads wisely\nStale indices — After modifying BAM/VCF, regenerate index. Old index = corrupt reads\n0-based vs 1-based coordinates — BED is 0-based, VCF/GFF is 1-based. Off-by-one bugs are common\nFile Formats Quick Reference\nFormat\tPurpose\tKey Tool\nFASTA\tReference sequences\tsamtools faidx\nFASTQ\tRaw reads + quality\tseqtk, fastp\nSAM/BAM\tAligned reads\tsamtools\nVCF/BCF\tVariants\tbcftools\nBED\tGenomic intervals\tbedtools\nGFF/GTF\tGene annotations\tgffread\nBigWig\tCoverage tracks\tdeepTools\nEssential Commands\nQuality Control\n# FASTQ quality report\nfastqc sample.fastq.gz -o qc_reports/\n\n# Trim adapters + low quality\nfastp -i R1.fq.gz -I R2.fq.gz -o R1.clean.fq.gz -O R2.clean.fq.gz\n\n# BAM statistics\nsamtools flagstat aligned.bam\nsamtools stats aligned.bam > stats.txt\n\nAlignment\n# Index reference (once)\nbwa index reference.fa\n\n# Align paired-end reads\nbwa mem -t 8 reference.fa R1.fq.gz R2.fq.gz | \\\n  samtools sort -o aligned.bam -\n\n# Index BAM\nsamtools index aligned.bam\n\nVariant Calling\n# Call variants\nbcftools mpileup -Ou -f reference.fa aligned.bam | \\\n  bcftools call -mv -Oz -o variants.vcf.gz\n\n# Index VCF\nbcftools index variants.vcf.gz\n\n# Filter variants\nbcftools filter -s LowQual -e 'QUAL<20' variants.vcf.gz\n\nData Manipulation\n# Extract region\nsamtools view -b aligned.bam chr1:1000000-2000000 > region.bam\n\n# Convert BAM to FASTQ\nsamtools fastq -1 R1.fq.gz -2 R2.fq.gz aligned.bam\n\n# Merge BAMs\nsamtools merge merged.bam sample1.bam sample2.bam\n\n# Subset VCF by region\nbcftools view -r chr1:1000-2000 variants.vcf.gz\n\nSecurity & Privacy\n\nData access:\n\nOnly reads files user explicitly provides as input\nWrites outputs to directories user specifies\nStores preferences in ~/bioinformatics/ (with consent)\n\nData that stays local:\n\nAll sequence data processed locally\nNo external API calls for analysis\nPipeline configs in ~/bioinformatics/\n\nThis skill does NOT:\n\nUpload sequence data anywhere\nAccess files without explicit user instruction\nInfer or collect data beyond explicit inputs\nMake network requests during analysis\n\nNote: Installing tools (conda, brew) and downloading reference genomes requires internet access. These are user-initiated actions.\n\nRelated Skills\n\nInstall with clawhub install <slug> if user confirms:\n\ndata-analysis — statistical interpretation\nstatistics — hypothesis testing\nscience — research methodology\nFeedback\nIf useful: clawhub star bioinformatics\nStay updated: clawhub sync"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/bioinformatics",
    "publisherUrl": "https://clawhub.ai/ivangdavila/bioinformatics",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/bioinformatics",
    "downloadUrl": "https://openagent3.xyz/downloads/bioinformatics",
    "agentUrl": "https://openagent3.xyz/skills/bioinformatics/agent",
    "manifestUrl": "https://openagent3.xyz/skills/bioinformatics/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/bioinformatics/agent.md"
  }
}