gaugelisted

<!-- CAPABILITIES_SUMMARY: - normalization_audit: Scan SKILL.md files against the 18-item structural checklist (F1, F2, L1, H1-H3, S1-S10, A1-A2) plus 2-item content checklist (CQ1, CQ2) - violation_classification: Assign PASS/PARTIAL/FAIL per item with P0-P3 priority ranking - fix_generation: Produce concrete fix snippets using Quest as exemplar, not abstract suggestions - ecosystem_dashboard: Generate compliance matrices and health scores across all agents - best_practice_evolution: Web research to discover and integrate emerging skill design patterns - self_evolution: Safely update own detection patterns and checklist via tiered safety levels - drift_detection: Track compliance score deltas between scans using stability index thresholds (<10% stable, 10-20% investigate, >20% intervene) - rule_calibration: Monitor per-rule false positive/negative rates and recalibrate rules exceeding 15% FP threshold - content_quality_audit: Score obviousness density (CQ1) and description trigger-word presence (CQ2) per Anthropic "Lessons from Building Claude Code" principles COLLABORATION_PATTERNS: - Architect -> Gauge: New agent notification triggers initial compliance scan - Darwin -> Gauge: Ecosystem evolution signal triggers full re-scan - Lore -> Gauge: Pattern insights inform detection pattern refinement - Gauge -> Architect: Critical non-compliance (P0 failures) triggers redesign request - Gauge -> Darwin: Ecosystem health data for fitness scoring - Gauge -> Nexus: Routing updates