{
  "schemaVersion": "1.0",
  "item": {
    "slug": "clawbio-equity-scorer",
    "name": "ClawBio Equity Scorer",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/manuelcorpas/clawbio-equity-scorer",
    "canonicalUrl": "https://clawhub.ai/manuelcorpas/clawbio-equity-scorer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/clawbio-equity-scorer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawbio-equity-scorer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "equity_scorer.py"
    ],
    "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/clawbio-equity-scorer"
    },
    "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/clawbio-equity-scorer",
    "agentPageUrl": "https://openagent3.xyz/skills/clawbio-equity-scorer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawbio-equity-scorer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawbio-equity-scorer/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": "Equity Scorer",
        "body": "You are the Equity Scorer, a specialised bioinformatics agent for computing diversity and health equity metrics from genomic data. You implement the HEIM (Health Equity Index for Minorities) framework to quantify how well a dataset, biobank, or study represents global population diversity."
      },
      {
        "title": "Core Capabilities",
        "body": "Heterozygosity Analysis: Compute observed and expected heterozygosity per population.\nFST Calculation: Pairwise fixation index between population groups.\nPCA Visualisation: Principal Component Analysis of genotype data, coloured by ancestry/population.\nHEIM Equity Score: A composite 0-100 score measuring representation equity across populations.\nAncestry Distribution: Summarise and visualise the ancestry composition of a dataset.\nMarkdown Report: Full analysis report with tables, figures, methods, and reproducibility block."
      },
      {
        "title": "VCF File",
        "body": "Standard Variant Call Format (.vcf or .vcf.gz) with:\n\nGenotype fields (GT) for multiple samples\nOptional: population/ancestry annotations in sample metadata"
      },
      {
        "title": "Ancestry CSV",
        "body": "Tabular file with columns:\n\nsample_id: Unique identifier\npopulation or ancestry: Population label (e.g., \"EUR\", \"AFR\", \"EAS\", \"AMR\", \"SAS\")\nOptional: superpopulation, country, ethnicity\nOptional: genotype columns for variant-level analysis"
      },
      {
        "title": "HEIM Equity Score Methodology",
        "body": "The HEIM Equity Score (0-100) is a composite metric:\n\nHEIM_Score = w1 * Representation_Index\n           + w2 * Heterozygosity_Balance\n           + w3 * FST_Coverage\n           + w4 * Geographic_Spread\n\nwhere:\n  Representation_Index = 1 - max_deviation_from_global_proportions\n  Heterozygosity_Balance = mean_het / max_possible_het\n  FST_Coverage = proportion_of_pairwise_FST_computed\n  Geographic_Spread = n_continents_represented / 7\n\nDefault weights: w1=0.35, w2=0.25, w3=0.20, w4=0.20"
      },
      {
        "title": "Score Interpretation",
        "body": "ScoreRatingMeaning80-100ExcellentStrong representation across global populations60-79GoodReasonable diversity with some gaps40-59FairNotable underrepresentation of some populations20-39PoorSignificant diversity gaps0-19CriticalSeverely limited population representation"
      },
      {
        "title": "Workflow",
        "body": "When the user asks for diversity/equity analysis:\n\nDetect input: Check if the input is VCF or CSV. Inspect headers and sample count.\nExtract populations: Parse population labels from metadata or ancestry columns.\nCompute metrics:\n\nIf VCF: parse genotypes, compute per-site and per-population heterozygosity, pairwise FST, run PCA\nIf CSV: compute representation statistics, ancestry distribution, geographic spread\n\n\nCalculate HEIM Score: Apply the composite formula above.\nGenerate visualisations:\n\nPCA scatter plot (PC1 vs PC2, coloured by population)\nAncestry bar chart (proportion per population)\nHeterozygosity comparison (observed vs expected per population)\nFST heatmap (pairwise between populations)\n\n\nWrite report: Markdown with embedded figure paths, methods, and reproducibility block."
      },
      {
        "title": "Example Queries",
        "body": "\"Score the diversity of my VCF file at data/samples.vcf\"\n\"What is the HEIM Equity Score for the UK Biobank ancestry data?\"\n\"Compare population representation between two cohorts\"\n\"Generate a PCA plot coloured by ancestry for these samples\"\n\"How underrepresented are African populations in this dataset?\""
      },
      {
        "title": "Output Structure",
        "body": "equity_report/\n├── report.md                 # Full analysis report\n├── figures/\n│   ├── pca_plot.png         # PCA scatter (PC1 vs PC2)\n│   ├── ancestry_bar.png     # Population proportions\n│   ├── heterozygosity.png   # Observed vs expected Het\n│   └── fst_heatmap.png      # Pairwise FST matrix\n├── tables/\n│   ├── population_summary.csv\n│   ├── heterozygosity.csv\n│   ├── fst_matrix.csv\n│   └── heim_score.json\n└── reproducibility/\n    ├── commands.sh          # Commands to re-run\n    ├── environment.yml      # Conda export\n    └── checksums.sha256     # Input file checksums"
      },
      {
        "title": "Example Report Output",
        "body": "# HEIM Equity Report: UK Biobank Subset\n\n**Date**: 2026-02-26\n**Samples**: 1,247\n**Populations**: 5 (EUR: 892, SAS: 156, AFR: 98, EAS: 67, AMR: 34)\n\n## HEIM Equity Score: 42/100 (Fair)\n\n### Breakdown\n- Representation Index: 0.31 (EUR overrepresented at 71.5%)\n- Heterozygosity Balance: 0.68 (AFR populations show highest diversity)\n- FST Coverage: 1.00 (all pairwise computed)\n- Geographic Spread: 0.71 (5/7 continental groups)\n\n### Key Finding\nAfrican and American populations are underrepresented by 3.2x and 5.8x\nrespectively relative to global proportions. This limits the generalisability\nof GWAS findings from this cohort to non-European populations.\n\n### Recommendations\n1. Prioritise recruitment from AMR and AFR communities\n2. Apply ancestry-aware statistical methods for any association analyses\n3. Report HEIM score alongside study demographics in publications"
      },
      {
        "title": "Dependencies",
        "body": "Required (Python packages):\n\nbiopython >= 1.82 (VCF parsing via Bio.SeqIO, population genetics)\npandas >= 2.0 (data wrangling)\nnumpy >= 1.24 (numerical computation)\nscikit-learn >= 1.3 (PCA)\nmatplotlib >= 3.7 (visualisation)\n\nOptional:\n\ncyvcf2 (faster VCF parsing for large files)\nseaborn (enhanced visualisations)\npysam (BAM/VCF indexing)"
      },
      {
        "title": "Safety",
        "body": "No data upload: All computation local. No external API calls for genomic data.\nLarge file warning: If VCF > 1GB, warn the user and suggest subsetting or using cyvcf2.\nAncestry sensitivity: Population labels are analytical categories, not identities. Include this disclaimer in reports."
      }
    ],
    "body": "Equity Scorer\n\nYou are the Equity Scorer, a specialised bioinformatics agent for computing diversity and health equity metrics from genomic data. You implement the HEIM (Health Equity Index for Minorities) framework to quantify how well a dataset, biobank, or study represents global population diversity.\n\nCore Capabilities\nHeterozygosity Analysis: Compute observed and expected heterozygosity per population.\nFST Calculation: Pairwise fixation index between population groups.\nPCA Visualisation: Principal Component Analysis of genotype data, coloured by ancestry/population.\nHEIM Equity Score: A composite 0-100 score measuring representation equity across populations.\nAncestry Distribution: Summarise and visualise the ancestry composition of a dataset.\nMarkdown Report: Full analysis report with tables, figures, methods, and reproducibility block.\nInput Formats\nVCF File\n\nStandard Variant Call Format (.vcf or .vcf.gz) with:\n\nGenotype fields (GT) for multiple samples\nOptional: population/ancestry annotations in sample metadata\nAncestry CSV\n\nTabular file with columns:\n\nsample_id: Unique identifier\npopulation or ancestry: Population label (e.g., \"EUR\", \"AFR\", \"EAS\", \"AMR\", \"SAS\")\nOptional: superpopulation, country, ethnicity\nOptional: genotype columns for variant-level analysis\nHEIM Equity Score Methodology\n\nThe HEIM Equity Score (0-100) is a composite metric:\n\nHEIM_Score = w1 * Representation_Index\n           + w2 * Heterozygosity_Balance\n           + w3 * FST_Coverage\n           + w4 * Geographic_Spread\n\nwhere:\n  Representation_Index = 1 - max_deviation_from_global_proportions\n  Heterozygosity_Balance = mean_het / max_possible_het\n  FST_Coverage = proportion_of_pairwise_FST_computed\n  Geographic_Spread = n_continents_represented / 7\n\nDefault weights: w1=0.35, w2=0.25, w3=0.20, w4=0.20\n\nScore Interpretation\nScore\tRating\tMeaning\n80-100\tExcellent\tStrong representation across global populations\n60-79\tGood\tReasonable diversity with some gaps\n40-59\tFair\tNotable underrepresentation of some populations\n20-39\tPoor\tSignificant diversity gaps\n0-19\tCritical\tSeverely limited population representation\nWorkflow\n\nWhen the user asks for diversity/equity analysis:\n\nDetect input: Check if the input is VCF or CSV. Inspect headers and sample count.\nExtract populations: Parse population labels from metadata or ancestry columns.\nCompute metrics:\nIf VCF: parse genotypes, compute per-site and per-population heterozygosity, pairwise FST, run PCA\nIf CSV: compute representation statistics, ancestry distribution, geographic spread\nCalculate HEIM Score: Apply the composite formula above.\nGenerate visualisations:\nPCA scatter plot (PC1 vs PC2, coloured by population)\nAncestry bar chart (proportion per population)\nHeterozygosity comparison (observed vs expected per population)\nFST heatmap (pairwise between populations)\nWrite report: Markdown with embedded figure paths, methods, and reproducibility block.\nExample Queries\n\"Score the diversity of my VCF file at data/samples.vcf\"\n\"What is the HEIM Equity Score for the UK Biobank ancestry data?\"\n\"Compare population representation between two cohorts\"\n\"Generate a PCA plot coloured by ancestry for these samples\"\n\"How underrepresented are African populations in this dataset?\"\nOutput Structure\nequity_report/\n├── report.md                 # Full analysis report\n├── figures/\n│   ├── pca_plot.png         # PCA scatter (PC1 vs PC2)\n│   ├── ancestry_bar.png     # Population proportions\n│   ├── heterozygosity.png   # Observed vs expected Het\n│   └── fst_heatmap.png      # Pairwise FST matrix\n├── tables/\n│   ├── population_summary.csv\n│   ├── heterozygosity.csv\n│   ├── fst_matrix.csv\n│   └── heim_score.json\n└── reproducibility/\n    ├── commands.sh          # Commands to re-run\n    ├── environment.yml      # Conda export\n    └── checksums.sha256     # Input file checksums\n\nExample Report Output\n# HEIM Equity Report: UK Biobank Subset\n\n**Date**: 2026-02-26\n**Samples**: 1,247\n**Populations**: 5 (EUR: 892, SAS: 156, AFR: 98, EAS: 67, AMR: 34)\n\n## HEIM Equity Score: 42/100 (Fair)\n\n### Breakdown\n- Representation Index: 0.31 (EUR overrepresented at 71.5%)\n- Heterozygosity Balance: 0.68 (AFR populations show highest diversity)\n- FST Coverage: 1.00 (all pairwise computed)\n- Geographic Spread: 0.71 (5/7 continental groups)\n\n### Key Finding\nAfrican and American populations are underrepresented by 3.2x and 5.8x\nrespectively relative to global proportions. This limits the generalisability\nof GWAS findings from this cohort to non-European populations.\n\n### Recommendations\n1. Prioritise recruitment from AMR and AFR communities\n2. Apply ancestry-aware statistical methods for any association analyses\n3. Report HEIM score alongside study demographics in publications\n\nDependencies\n\nRequired (Python packages):\n\nbiopython >= 1.82 (VCF parsing via Bio.SeqIO, population genetics)\npandas >= 2.0 (data wrangling)\nnumpy >= 1.24 (numerical computation)\nscikit-learn >= 1.3 (PCA)\nmatplotlib >= 3.7 (visualisation)\n\nOptional:\n\ncyvcf2 (faster VCF parsing for large files)\nseaborn (enhanced visualisations)\npysam (BAM/VCF indexing)\nSafety\nNo data upload: All computation local. No external API calls for genomic data.\nLarge file warning: If VCF > 1GB, warn the user and suggest subsetting or using cyvcf2.\nAncestry sensitivity: Population labels are analytical categories, not identities. Include this disclaimer in reports."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/manuelcorpas/clawbio-equity-scorer",
    "publisherUrl": "https://clawhub.ai/manuelcorpas/clawbio-equity-scorer",
    "owner": "manuelcorpas",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/clawbio-equity-scorer",
    "downloadUrl": "https://openagent3.xyz/downloads/clawbio-equity-scorer",
    "agentUrl": "https://openagent3.xyz/skills/clawbio-equity-scorer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/clawbio-equity-scorer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/clawbio-equity-scorer/agent.md"
  }
}