{ "rubric": "K1-K9", "note": "Deterministic: K2,K3,K5,K6,refCountConsistency. LLM-judge (operator-gated): K1,K4,K7,K8,K9.", "skills": [ { "name": "ms-ai-advisor", "skillMd": "skills/ms-ai-advisor/SKILL.md", "refFilesActual": 62, "refCountsPerFolder": { "architecture": 16, "copilot-extensibility": 22, "development": 1, "platforms": 5, "prompt-engineering": 18 }, "deterministic": { "K2_descriptionFormat": { "quotedPhrases": 5, "useWhenForm": true, "imperativeStart": false, "pass": true }, "K3_bodyLength": { "bodyLines": 240, "pass": true }, "K5_progressiveDisclosure": { "namedFileLinks": 1, "folderRefs": 5, "totalRefFiles": 62, "namedRatio": 0.0161, "pass": false, "sampleNamed": [ "references/architecture/diagram-prompt-templates.md" ] }, "K6_routingTable": { "namedStartFiles": 1, "pass": true }, "refCountConsistency": { "consistent": true, "mismatches": [] }, "K9_timeSensitiveHints": { "timeSensitiveTokenHits": 7, "sample": [ "Preview", "GA", "preview", "v3.0" ] } }, "judgeInputs": { "description": "Microsoft AI architecture guidance, choosing between Azure AI platforms, Copilot vs Foundry trade-offs. Cosmo Skyberg persona guides through structured problem understanding before technology selection. Specialist in Azure AI Foundry, M365 Copilot, Copilot Studio, Power Platform, Azure OpenAI, Microsoft Agent Framework. Triggers on: \"Microsoft AI architecture\", \"Copilot vs Foundry\", \"which Microsoft AI platform\", \"Cosmo\", \"/architect\".", "bodyLines": 240, "refFileSample": [ "skills/ms-ai-advisor/references/architecture/adr-template.md", "skills/ms-ai-advisor/references/architecture/ai-utredning-template.md", "skills/ms-ai-advisor/references/architecture/alternativanalyse-methodology.md", "skills/ms-ai-advisor/references/architecture/capacity-feasibility-benchmarks.md", "skills/ms-ai-advisor/references/architecture/cost-models.md", "skills/ms-ai-advisor/references/architecture/decision-trees.md", "skills/ms-ai-advisor/references/architecture/diagram-prompt-templates.md", "skills/ms-ai-advisor/references/architecture/licensing-matrix.md" ] }, "judge": { "K1_triggerPrecision": { "provisional": true, "precision": 1, "notes": "20/20 from description. BORDERLINE: cost/diagram/DPIA/AI-Act prompts are MS-AI-adjacent; broad 'Microsoft AI architecture' phrase risks over-triggering vs sibling commands. Operator must curate + stress-test sibling overlap." }, "K4_noDuplication": { "score": 5, "pass": true, "evidence": "Body = persona + 7-phase workflow + ref-index; no ref detail reproduced. Only internal MCP-table redundancy (SKILL-internal, not SKILL<->ref)." }, "K7_imperativeStyle": { "ratio": 1, "pass": true, "notes": "10/10 sampled instruction sentences imperative." }, "K8_sourceCitation": { "ratio": 0.8, "pass": true, "notes": "AT THRESHOLD: architecture/decision-trees.md lacks dated header (footer source only). Add dated header to harden margin." }, "K9_noTimeSensitive": { "pass": true, "findings": [ "Only meta-instructions (preview/GA as dynamic-to-verify) + stable identifiers (M365 SKUs, MADR v3.0). No stale-able product claim in body." ] } } }, { "name": "ms-ai-engineering", "skillMd": "skills/ms-ai-engineering/SKILL.md", "refFilesActual": 153, "refCountsPerFolder": { "agent-orchestration": 24, "api-management": 19, "azure-ai-services": 20, "data-engineering": 22, "mlops-genaiops": 22, "multi-modal": 18, "rag-architecture": 28 }, "deterministic": { "K2_descriptionFormat": { "quotedPhrases": 6, "useWhenForm": true, "imperativeStart": false, "pass": true }, "K3_bodyLength": { "bodyLines": 150, "pass": true }, "K5_progressiveDisclosure": { "namedFileLinks": 0, "folderRefs": 10, "totalRefFiles": 153, "namedRatio": 0, "pass": false, "sampleNamed": [] }, "K6_routingTable": { "namedStartFiles": 0, "pass": false }, "refCountConsistency": { "consistent": false, "mismatches": [ { "folder": "agent-orchestration", "cited": 20, "actual": 24 }, { "folder": "agent-orchestration", "citedMultiple": [ 24, 20 ], "actual": 24 } ] }, "K9_timeSensitiveHints": { "timeSensitiveTokenHits": 3, "sample": [ "GA", "preview" ] } }, "judgeInputs": { "description": "Deep technical guidance for building AI solutions in the Microsoft stack — RAG architecture, multi-agent orchestration, Azure AI Services, data engineering with Fabric, MLOps/GenAIOps, multimodal AI, API Management for AI. Triggers on: \"RAG architecture on Azure\", \"multi-agent orchestration pattern\", \"MLOps for generative AI\", \"Azure AI Search\", \"Semantic Kernel agent\", \"Fabric data pipeline\".", "bodyLines": 150, "refFileSample": [ "skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md", "skills/ms-ai-engineering/references/agent-orchestration/agent-autonomy-and-control-governance.md", "skills/ms-ai-engineering/references/agent-orchestration/agent-compliance-and-audit-trails.md", "skills/ms-ai-engineering/references/agent-orchestration/agent-cost-optimization-strategies.md", "skills/ms-ai-engineering/references/agent-orchestration/agent-ecosystem-and-plugin-marketplace.md", "skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md", "skills/ms-ai-engineering/references/agent-orchestration/agent-feedback-and-learning-loops.md", "skills/ms-ai-engineering/references/agent-orchestration/agent-latency-optimization.md" ] }, "judge": { "K1_triggerPrecision": { "provisional": true, "precision": 0.95, "notes": "19/20. Miss: 'Semantic Kernel agent governance' overlaps security/governance because description lists 'governance' under agent-orchestration. Operator must curate." }, "K4_noDuplication": { "score": 4, "pass": true, "evidence": "Mostly router. Two inline tables (RAG-vs-finetuning; MLOps test-types w/ Ragas/red-teaming) restate comparison content also in ref files — summary-level, not verbatim." }, "K7_imperativeStyle": { "ratio": 0.9, "pass": true, "notes": "9/10; section intros are descriptive prose by design." }, "K8_sourceCitation": { "ratio": 1, "pass": true, "notes": "5/5 dated headers; schema drift ('Dato:' vs 'Last updated'); no source-URL in headers." }, "K9_noTimeSensitive": { "pass": false, "findings": [ "Line 119: 'Foundry Agent Service GA' — explicit GA-status claim in body", "GPT-4o/Whisper/text-embedding-3/Florence — version-pinned product names in body", "Line 48: 'Agent Framework (erstatter Semantic Kernel Agents)' — lifecycle/transition claim", "A2A/CUA/Foundry Workflows — era-bound feature names" ] } } }, { "name": "ms-ai-governance", "skillMd": "skills/ms-ai-governance/SKILL.md", "refFilesActual": 78, "refCountsPerFolder": { "monitoring-observability": 18, "norwegian-public-sector-governance": 30, "responsible-ai": 30 }, "deterministic": { "K2_descriptionFormat": { "quotedPhrases": 6, "useWhenForm": true, "imperativeStart": false, "pass": true }, "K3_bodyLength": { "bodyLines": 299, "pass": true }, "K5_progressiveDisclosure": { "namedFileLinks": 24, "folderRefs": 5, "totalRefFiles": 78, "namedRatio": 0.3077, "pass": true, "sampleNamed": [ "references/norwegian-public-sector-governance/utredningsinstruksen-ai-methodology.md", "references/norwegian-public-sector-governance/forvaltningsloven-ai-decisions.md", "references/norwegian-public-sector-governance/samfunnsokonomisk-analyse-nnv.md", "references/norwegian-public-sector-governance/gevinstrealisering-dfo-methodology.md", "references/norwegian-public-sector-governance/anskaffelser-ai-procurement-framework.md" ] }, "K6_routingTable": { "namedStartFiles": 24, "pass": true }, "refCountConsistency": { "consistent": false, "mismatches": [ { "folder": "norwegian-public-sector-governance", "cited": 29, "actual": 30 } ] }, "K9_timeSensitiveHints": { "timeSensitiveTokenHits": 1, "sample": [ "2024" ] } }, "judgeInputs": { "description": "Norwegian public sector AI compliance, utredningsinstruksen for AI, EU AI Act risk classification, DPIA for AI systems, Digdir architecture principles, responsible AI governance, monitoring and observability. Triggers on: \"Norwegian public sector AI compliance\", \"AI Act risk classification\", \"DPIA for AI system\", \"Digdir architecture principles\", \"ansvarlig AI i offentlig sektor\", \"Forvaltningsloven AI\".", "bodyLines": 299, "refFileSample": [ "skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md", "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md", "skills/ms-ai-governance/references/monitoring-observability/application-insights-llm-monitoring.md", "skills/ms-ai-governance/references/monitoring-observability/azure-monitor-setup-ai-workloads.md", "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md", "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md", "skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md", "skills/ms-ai-governance/references/monitoring-observability/data-residency-audit-monitoring.md" ] }, "judge": { "K1_triggerPrecision": { "provisional": true, "precision": 0.95, "notes": "19/20. Miss: Schrems II / data-transfer — body section 2.3 covers it but description has NO Schrems/dataoverføring keyword. Add trigger phrase to description." }, "K4_noDuplication": { "score": 3, "pass": false, "evidence": "Moderate duplication: §6.1 DPIA risk-factor tree (incl. >=2-faktorer threshold) duplicates dpia-norwegian-methodology-ai.md; §6.2 + §2.1 AI Act taxonomy duplicates ai-act-classification-methodology.md; §1.2 Digdir 7-principle table restates per-principle files. Regulatory update must be applied twice." }, "K7_imperativeStyle": { "ratio": 1, "pass": true, "notes": "10/10 imperative." }, "K8_sourceCitation": { "ratio": 1, "pass": true, "notes": "5/5 dated headers + Status + inline source citations (Lovdata/NSM/europalov). BONUS DEFECT: SKILL.md line 191 references 'drift-detection-automated-retraining.md' which does NOT exist (actual: model-performance-drift-detection.md) — broken ref path." }, "K9_noTimeSensitive": { "pass": false, "findings": [ "Line 121: 'Microsoft EU Data Boundary ... Azure OpenAI (Sweden Central, West Europe)' — volatile region/availability claim in body (most genuine finding)", "Lines 81/121: 'Regulation 2024/1689' + 'Schrems II (C-311/18)' — legal identifiers (stable, borderline)", "§2.1/§6.2 AI Act obligation status presented without Digital Omnibus caveat — may date" ] } } }, { "name": "ms-ai-infrastructure", "skillMd": "skills/ms-ai-infrastructure/SKILL.md", "refFilesActual": 34, "refCountsPerFolder": { "bcdr": 16, "hybrid-edge": 18 }, "deterministic": { "K2_descriptionFormat": { "quotedPhrases": 5, "useWhenForm": true, "imperativeStart": false, "pass": true }, "K3_bodyLength": { "bodyLines": 290, "pass": true }, "K5_progressiveDisclosure": { "namedFileLinks": 33, "folderRefs": 5, "totalRefFiles": 34, "namedRatio": 0.9706, "pass": true, "sampleNamed": [ "references/bcdr/multi-region-azure-openai-deployment.md", "references/bcdr/rto-rpo-planning-ai-services.md", "references/bcdr/backup-recovery-strategies-ai-workloads.md", "references/bcdr/failover-testing-ai-services.md", "references/bcdr/chaos-engineering-ai-systems.md" ] }, "K6_routingTable": { "namedStartFiles": 33, "pass": true }, "refCountConsistency": { "consistent": true, "mismatches": [] }, "K9_timeSensitiveHints": { "timeSensitiveTokenHits": 7, "sample": [ "preview", "GA", "v2" ] } }, "judgeInputs": { "description": "Disaster recovery for AI workloads, multi-region Azure AI deployment, hybrid or edge AI architecture, sovereign cloud for Norway, offline-first AI patterns, AI infrastructure resilience. Covers BCDR, Azure Arc for AI, ONNX Runtime edge deployment, disconnected scenarios, Norwegian data sovereignty. Triggers on: \"disaster recovery for AI workloads\", \"edge AI deployment\", \"sovereign cloud AI\", \"Azure Arc for AI\", \"BCDR for AI\".", "bodyLines": 290, "refFileSample": [ "skills/ms-ai-infrastructure/references/bcdr/ai-foundry-disaster-recovery-planning.md", "skills/ms-ai-infrastructure/references/bcdr/backup-recovery-strategies-ai-workloads.md", "skills/ms-ai-infrastructure/references/bcdr/capacity-planning-dr-configurations.md", "skills/ms-ai-infrastructure/references/bcdr/chaos-engineering-ai-systems.md", "skills/ms-ai-infrastructure/references/bcdr/compliance-requirements-bcdr.md", "skills/ms-ai-infrastructure/references/bcdr/cost-analysis-dr-configurations.md", "skills/ms-ai-infrastructure/references/bcdr/data-replication-patterns-ai.md", "skills/ms-ai-infrastructure/references/bcdr/failover-testing-ai-services.md" ] }, "judge": { "K1_triggerPrecision": { "provisional": true, "precision": 1, "notes": "20/20. Tightly scoped + named trigger phrases, low false-positive risk. Borderline (hybrid RAG, multi-region cost) need real-corpus validation. Operator must curate." }, "K4_noDuplication": { "score": 4, "pass": true, "evidence": "Largely summary/routing w/ '> Ref:' deferral. Minor: RTO/RPO table + SLA table put specific values in body that also live in ref files." }, "K7_imperativeStyle": { "ratio": 1, "pass": true, "notes": "10/10 imperative (concentrated in per-section directives)." }, "K8_sourceCitation": { "ratio": 1, "pass": true, "notes": "5/5 'Last updated: 2026-02' + Status. NO source-URL in headers; identical batch date reads as generation timestamp, not per-file verification." }, "K9_noTimeSensitive": { "pass": false, "findings": [ "Lines 93-98: SLA table w/ hardcoded percentages (99.9/99.999/99.95%) + 'Standard v2'", "Lines 149/158/184/186/249: Phi-3/Phi-4 model versions + param counts (3.8B/14B) in body", "Line 141: 'Azure Local (tidl. Azure Stack HCI)' rename note", "Line 87: hardcoded 'peak + 30% buffer'" ] } } }, { "name": "ms-ai-security", "skillMd": "skills/ms-ai-security/SKILL.md", "refFilesActual": 62, "refCountsPerFolder": { "ai-security-engineering": 22, "cost-optimization": 22, "performance-scalability": 18 }, "deterministic": { "K2_descriptionFormat": { "quotedPhrases": 6, "useWhenForm": true, "imperativeStart": false, "pass": true }, "K3_bodyLength": { "bodyLines": 212, "pass": true }, "K5_progressiveDisclosure": { "namedFileLinks": 10, "folderRefs": 6, "totalRefFiles": 62, "namedRatio": 0.1613, "pass": false, "sampleNamed": [ "references/ai-security-engineering/security-scoring-rubrics-6x5.md", "references/ai-security-engineering/ai-security-scoring-framework.md", "references/ai-security-engineering/secure-model-deployment-hardening.md", "references/ai-security-engineering/zero-trust-ai-services.md", "references/cost-optimization/deterministic-cost-calculation-model.md" ] }, "K6_routingTable": { "namedStartFiles": 10, "pass": true }, "refCountConsistency": { "consistent": true, "mismatches": [] }, "K9_timeSensitiveHints": { "timeSensitiveTokenHits": 3, "sample": [ "2025", "GA", "Preview" ] } }, "judgeInputs": { "description": "Security assessment, cost estimation, OWASP LLM Top 10 mitigations, performance optimization for AI on Microsoft stack. Deterministic 6x5 security scoring, P10/P50/P90 cost confidence intervals, FinOps practices. Triggers on: \"security assessment for AI\", \"AI threat modeling\", \"cost estimation for Azure AI\", \"FinOps for AI workloads\", \"OWASP LLM\", \"kostnadsestimat for AI-løsning\".", "bodyLines": 212, "refFileSample": [ "skills/ms-ai-security/references/ai-security-engineering/adversarial-input-robustness-testing.md", "skills/ms-ai-security/references/ai-security-engineering/ai-incident-response-procedures.md", "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md", "skills/ms-ai-security/references/ai-security-engineering/ai-red-team-operations-practical.md", "skills/ms-ai-security/references/ai-security-engineering/ai-security-scoring-framework.md", "skills/ms-ai-security/references/ai-security-engineering/ai-threat-modeling-stride.md", "skills/ms-ai-security/references/ai-security-engineering/content-safety-filter-calibration.md", "skills/ms-ai-security/references/ai-security-engineering/data-leakage-prevention-ai.md" ] }, "judge": { "K1_triggerPrecision": { "provisional": true, "precision": 0.95, "notes": "19/20. Clean sibling separation (AI Act/DPIA/platform/RAG/BCDR not triggered). One ambiguity: model feature-comparison could be pulled by broad 'performance optimization for AI'. Operator must curate." }, "K4_noDuplication": { "score": 3, "pass": false, "evidence": "DUPLICATION-WITH-CONTRADICTION: body weighting table (L52-59 Standard: Identity 20/Network 15/Data 20/Content 20/Compliance 15/Monitoring 10) CONTRADICTS canonical rubric security-scoring-rubrics-6x5.md (Compliance 25/Data 20/Identity 20/Content 15/Network 10/Monitoring 10). Body scoring rule (weighted sum) also diverges from rubric (Ja-checkpoint count). Real correctness bug." }, "K7_imperativeStyle": { "ratio": 1, "pass": true, "notes": "10/10 imperative." }, "K8_sourceCitation": { "ratio": 1, "pass": true, "notes": "5/5 dated headers; mostly no header source-URL (URLs in body cost-register rows)." }, "K9_noTimeSensitive": { "pass": false, "findings": [ "Line 73: 'OWASP LLM Top 10 (2025)' — dated standard version", "Line 92: 'Defender ... GA for AI applications, Preview for AI agents' + 'ikke i Azure Government' — GA/preview + region status in body", "Line 138: 'GPT-4o mini vs GPT-4o' — model versions", "Lines 149-153: hardcoded perf/price figures (20-50ms, 5-10x, 50%/80%, Batch 50% @ 24h SLA)" ] } } } ] }