U0172 Governance Human Approval Router

Governance Human Approval Router

Why This Skill Exists

We need this skill because high-speed autonomy needs enforceable guardrails to stay aligned. This specific skill directs high-risk decisions to the right humans quickly.

When To Use

Use this skill when the request explicitly needs "Governance Human Approval Router" outcomes in the Safety and Governance domain.

Step-by-Step Implementation Guide

1. Define the scope and success metrics for Governance Human Approval Router, including at least three measurable KPIs tied to unsafe actions and policy drift.
2. Design and version the input/output contract for policies, violations, and mitigation actions, then add schema validation and failure-mode handling.
3. Implement the core capability using reviewer routing policies, and produce priority approval queues with deterministic scoring.
4. Integrate the skill into swarm orchestration: task routing, approval gates, retry strategy, and rollback controls.
5. Add unit, integration, and simulation tests that explicitly cover unsafe actions and policy drift, then run regression baselines.
6. Deploy behind a feature flag, monitor telemetry/alerts for two release cycles, and iterate thresholds based on observed outcomes.

Required Deliverables

• Capability contract: input schema, deterministic scoring, output schema, and failure modes.
• Runtime profile: planning-router using reviewer routing policies to produce priority approval queues.
• Orchestration integration: safety-and-governance:planning-router routing, approval gates, retries, and rollback controls.
• Validation evidence: unit, integration, simulation, regression-baseline suites and rollout telemetry.

Operational Runbook

Preflight

• Confirm the Governance Human Approval Router request scope, source evidence, and measurable success criteria before execution.
• Verify feature flag skill_0172_governance-human-approval-router, approval gates, and rollback owner before autonomous use.

Execution

• Execute reviewer routing policies with deterministic scoring and reproducible trace capture.
• Produce priority approval queues plus scorecard, assumptions, and unresolved-risk notes.

Recovery

• Fail closed when required signals, evidence, or approval gates are missing.
• Rollback to the last stable baseline when posture is critical or validation fails.

Handoff

• Publish priority approval queues, validation evidence, and telemetry links to downstream owners.
• Queue follow-up tasks for unresolved risks, threshold tuning, or approval review.

Guardrails

• [quality] Require deterministic scoring and validation evidence before promotion.
• [reliability] Preserve retries, rollback controls, and failure-mode evidence for every run.
• [safety] Route critical posture or missing approval gates to human review before autonomous action.