Update to MUSITU Axiom

{
  "description": "Inspect data quality before quantitative analysis. Use for missingness, duplicates, schema drift, invalid ranges, inconsistent units, date errors, outliers, reconciliation, and analysis-readiness.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 208
    },
    {
      "relative_path": "references/COMMERCIAL.md",
      "size_in_bytes": 751
    },
    {
      "relative_path": "references/PROOF.md",
      "size_in_bytes": 537
    },
    {
      "relative_path": "references/QUALITY.md",
      "size_in_bytes": 2262
    },
    {
      "relative_path": "references/ROUTING.md",
      "size_in_bytes": 504
    },
    {
      "relative_path": "scripts/proof_envelope.py",
      "size_in_bytes": 1023
    },
    {
      "relative_path": "scripts/scenario_grid.py",
      "size_in_bytes": 691
    }
  ],
  "name": "musitu-data-quality",
  "skill_md_contents": "---\nname: musitu-data-quality\ndescription: \"Inspect data quality before quantitative analysis. Use for missingness, duplicates, schema drift, invalid ranges, inconsistent units, date errors, outliers, reconciliation, and analysis-readiness.\"\n---\n# MUSITU Data Quality\nRead `references/QUALITY.md`.\n\n## Workflow\n1. Inventory schema and expected semantics.\n2. Measure completeness, uniqueness and validity.\n3. Check unit, date, currency and category consistency.\n4. Detect duplicates, outliers and schema/distribution drift.\n5. Reconcile totals and identities where applicable.\n6. Classify defects by impact and confidence.\n7. Block downstream analysis when defects invalidate results.\n8. Return remediation steps and residual data risk.\n"
}