Update to MUSITU Axiom

{
  "description": "Design, validate, diagnose, and explain KPIs and business metrics. Use for metric definitions, denominator disputes, KPI trees, variance drivers, funnel metrics, and metric anomalies.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 244
    },
    {
      "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-kpi-metric-diagnostics",
  "skill_md_contents": "---\nname: musitu-kpi-metric-diagnostics\ndescription: \"Design, validate, diagnose, and explain KPIs and business metrics. Use for metric definitions, denominator disputes, KPI trees, variance drivers, funnel metrics, and metric anomalies.\"\n---\n# MUSITU KPI & Metric Diagnostics\nRead `references/QUALITY.md`.\n\n## Workflow\n1. Define the metric and denominator exactly.\n2. Trace source and transformation.\n3. Check time, cohort and population alignment.\n4. Decompose changes into drivers.\n5. Test alternate definitions and denominator choices.\n6. Identify measurement artifacts and broken comparability.\n7. Link the metric to a concrete decision or control loop.\n8. Return the canonical definition, diagnostic and caveats.\n"
}