SUPERSEDED — applied 2026-07-31. This update pack was applied in the v3.0 skill rollout; the live skill is skills/miz-oki-platform-expert/SKILL.md (parity-governed via scripts/skills_sync.py). Retained for history only. Banner added by the v2.2 compliance sweep, 2026-08-12.

miz-oki-platform-expert — SKILL.md v3.0 Update Pack

How to apply: This pack follows the skill's own per-section update mechanism. Replace the sections named below in the existing SKILL.md; insert the new skill sections (16–19) before the Quick Reference section. Everything not named here carries forward from v2.0 unchanged.

REPLACE: Header block

**Version**: 3.0
**Last Updated**: July 12, 2026
**Platform**: MIZ OKI 3.5 (MIZ Operating Knowledge Intelligence)
**Architecture**: 32-cell microservices + shared horizontal services, SRPVDAL framework
**Changelog**:
- v3.0 (2026-07-12): Aligned to Three-Domain Blueprint v2 — SRDAL→SRPVDAL; three Domain Intelligence Cells; Canonical Event Envelope; Validation Passports; Decision Control Plane; decision-object contracts; claims-labeling rule; measurement hierarchy corrected; Data Manager API connector rule; auth hardening requirements
- v2.0 (2026-03-15): Added Boss agent MCP tool mappings; restructured for single-file drop-in update
- v1.0 (2025-10-25): Initial 15-skill comprehensive guide

REPLACE: Overview

This skill guide enables Claude to support the MIZ OKI 3.5 platform — a governed decision-intelligence platform that turns fragmented evidence into validated, explainable, and authorized decisions. The platform is one shared temporal-causal knowledge graph and one Decision Control Plane serving multiple Domain Intelligence Cells; it is not a set of separate products.

Canonical operating loop (SRPVDAL):

Sense → Reason → Plan → Validate → Decide → Act → Learn

Canonical decision pathway:

Evidence → Canonical Event Envelope → Temporal-Causal KG → Domain ReasoningPath
→ Scenario/Forecast/Counterfactual → Validation Passport → Decision Eligibility
→ Authorized Action or Operator Gate → Outcome Learning

Domain Intelligence Cells (example deployments, not a product ceiling): 1. Predictive Financial Intelligence 2. Media Acquisition Intelligence 3. Commercial Real Estate Underwriting & Asset Risk

Key Platform Facts: - Cells: 32 FastAPI services on Google Cloud Run, plus shared horizontal services (ingestion, identity resolution, provenance/bitemporal lineage, GraphRAG/CausalRAG, counterfactual simulation, model registry, validation orchestrator, policy engine, decision control plane, approval routing, action runner, audit/replay, learning ledger, observability) - Data: BigQuery (unified dataset), Neo4j (temporal-causal KG), GCS, Pub/Sub, Firestore, Vertex AI - Frontend: React + TypeScript command center (/command-center, /knowledge-graph, /loops, /decisions, /simulations, /approvals, /audit, /learning, /channels/{finance|media|cre}) - Positioning rule: the platform metaphor is "nervous system," never "brain"

Claims-labeling rule (mandatory): every performance figure written anywhere — docs, code comments, marketing, emails — carries exactly one label: verified result | benchmark result | pilot result | design target | illustrative scenario. - Business goals (40% CAC reduction, 35% ROAS increase, 67% ROI improvement, 95%+ attribution accuracy): design targets - Sub-100ms latency, 99.9% availability: design targets until benchmark citations exist - ACT-991 ($5.0M blocked at DEL 41, re-routed to $3.2M): illustrative scenario — the canonical demo, never presented as a customer result

REPLACE: In Skill 3 (Causal Inference), the "Causal Framework Overview" block

Measurement Hierarchy (evidence strength, ascending):
1. Platform attribution            ← one claim, never ground truth
2. First-party journey evidence
3. Causal MMM (Meridian + Robyn run as complements; report divergence)
4. Geo / holdout / randomized experiment evidence (GeoLift or equivalent)
5. Incremental profit after margin, returns, inventory, and cost
   ← THE decision objective

Meta-learners (X-Learner Cell 26, DR-Learner Cell 27) are estimation tools
inside this hierarchy, not its apex. No model or platform is an oracle.

Also in Skill 3: the "Business Metrics Translation" block figures are design targets — label them as such wherever quoted.

REPLACE: In Skill 4 (FastAPI Backend), the auth guidance

Authentication requirements (supersedes v2.0 template): - Never deploy a cell with --allow-unauthenticated except the public API gateway. - Enforce Cloud Run IAM: each calling service account granted roles/run.invoker on exactly the cells it calls. - Verify Google-signed ID tokens (audience-checked against the receiving cell URL) — never compare bearer tokens to static strings.

from google.auth.transport import requests as ga_requests
from google.oauth2 import id_token

async def verify_oidc_token(authorization: str = Header(None)):
    if not authorization or not authorization.startswith("Bearer "):
        raise HTTPException(status_code=401, detail="Missing token")
    token = authorization.split(" ", 1)[1]
    try:
        claims = id_token.verify_oauth2_token(
            token, ga_requests.Request(), audience=SELF_URL)
        return {"service": claims["email"]}
    except ValueError:
        raise HTTPException(status_code=403, detail="Invalid token")

REPLACE: In Skill 9 (Marketing Attribution), connector rule

Connector rule: all new offline-conversion and enhanced-conversions-for-leads integrations are built on Google's Data Manager API. Legacy Google Ads API conversion-upload behavior is compatibility-only where still permitted, and must not be used for new work.

NEW — Skill 16: Canonical Event Envelope & Bitemporal Ingestion

Purpose

Every event enters the platform through one envelope with four time axes, enabling point-in-time integrity, provenance, and replay.

Core Capabilities

{
  "event_id": "stable_hash",
  "tenant_id": "tenant",
  "domain": "finance | media | cre",
  "entity_ids": [],
  "source_system": "system",
  "source_document_id": "optional",
  "occurred_at": "business_effective_time",
  "observed_at": "observation_time",
  "available_to_model_at": "point_in_time_availability",
  "ingested_at": "system_time",
  "schema_version": "version",
  "source_payload_hash": "hash",
  "confidence": 0.0,
  "verification_status": "verified | unverified | disputed",
  "materiality": "low | medium | high | critical",
  "provenance": {},
  "audit_id": "audit_record"
}

Best Practices

  1. Envelope is additive: wrap service-canonical-ingestion in front of existing SENSE cells; do not rewrite them.
  2. Historical backfill sets available_to_model_at conservatively to first-ingest time.
  3. source_payload_hash computed before any transformation.
  4. No model may train or backtest on events filtered by anything other than available_to_model_at.
  5. verification_status: disputed events surface in contradiction retrieval; they are never silently dropped.

NEW — Skill 17: Validation Orchestration & Validation Passports

Purpose

No candidate decision reaches Decide without a domain-specific Validation Passport issued by service-validation-orchestrator.

Core Capabilities

Best Practices

  1. Passports are immutable, versioned, and attached to the DecisionProof.
  2. A failed check never silently downgrades — it changes eligibility state.
  3. Baselines are always run alongside challengers; passports record both.
  4. Rejected candidate paths are recorded with their failing checks.
  5. Passport schemas live in the shared contracts package.

NEW — Skill 18: Decision Control Plane, Decision Objects & Staged Autonomy

Purpose

One governed pathway from validated candidate to authorized action.

Core Capabilities

Shared decision objects (versioned JSON Schemas in contracts/):

EvidenceBundle · ReasoningPath · ForecastOrScenario · ValidationPassport
· DecisionProof · ActionAuthorization · OutcomeRecord · LearningRecord

Eligibility state machine:

eligible | approval-required | experiment-required | advisory-only | blocked

Autonomy staging: - Stage 3 (default for all actuators): observe → explain → simulate → recommend → route for approval. - Stage 4 (earned per actuator): bounded, reversible, low-risk actions only, after evaluation, approval, rollback, and monitoring are proven. - Every actuator registers a rollback/compensating action or declares itself irreversible → permanently approval-gated. - ACT cells hard-refuse any request lacking a valid ActionAuthorization.

Cross-domain flow:

Media proposes growth spend
→ Finance validates cash, margin, payback
→ CRE validates location/lease/capacity where relevant
→ Decision Control Plane approves, gates, or vetoes

Best Practices

  1. Policy is declarative (policy-as-code), versioned, and replayable.
  2. Every DecisionProof records rejected alternatives.
  3. Approvals are routed, timestamped, and attributable to a human identity.
  4. Audit/replay must reconstruct any decision from evidence forward.
  5. No model serves a decision path without a model-registry entry and baseline comparison.

NEW — Skill 19: Domain Intelligence Cells — Status & Proof Obligations

Purpose

Track what is built versus what is proven, per cell. Implementation evidence ≠ validated business performance.

Status Ledger

Media Acquisition Intelligence — most mature; production attribution stack live. Open proof obligations: MMM calibration, geo/holdout experiment readouts, incremental-profit validation after margin/returns/inventory joins.

Predictive Financial Intelligence — services (service-financial-tckg, service-macro-regime, service-tgnn-forecast, service-financial-validation-lab) in buildout. Advisory-only until the finance passport battery passes. All outputs are challengers against transparent baselines.

CRE Underwriting & Asset Risk — implementation documented (integration exists, six tools registered, eight-layer engine, Monte Carlo, t-copula, Boss Agent runtime connection). Unproven and must be labeled as such: field extraction accuracy, lease/rent-roll reconciliation accuracy, NOI forecast accuracy, risk-detection recall, probability calibration, committee usefulness, time savings, loss avoidance, post-close surprise reduction. The Chrome Boss Agent extension is point-of-work capture, not the underwriting source of truth. CRE output supports underwriting; it never replaces appraisal, engineering, environmental, legal, fiduciary, lending, or investment-committee authority.

Best Practices

  1. Before feature work on CRE, run the Stage 2 benchmark battery: extraction benchmark, historical deal reconstruction, adversarial diligence, shadow underwriting, post-close outcomes.
  2. Never market cross-domain flows until two cells exchange real DecisionProof objects.
  3. New domains are added as cells on the shared graph — never as separate platforms.

End of v3.0 update pack. Sections not named above carry forward from v2.0 unchanged.

← All docsView source on GitHub →