메뉴
Use when reviewing Dataverse AI actions for permissions, policy validation, risk assessment, approval routing, auditability, and explainability. Produces governance guidance only; it does not enforce policies in a live tenant.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when the user wants to inspect or operate a real Microsoft Dataverse environment through the plugin MCP server with OAuth2 client credentials. Supports metadata, query, retrieve, create, update, delete, action execution, and simulation tools.
Use when applying the monetizable enterprise USP pack for Dataverse and Power Platform: compliance evidence automation, ROI and process value scoring, autonomous remediation playbooks, tenant-specific AI skill generation, governed cross-tenant rollout, business capability mapping, trust scoring for AI actions, autonomous exception management, enterprise change impact AI, and AI-controlled operating cadence.
Use when applying the advanced AI USP expansion for Dataverse and Power Platform: organizational cognitive graph, autonomous reasoning, self-optimization, process discovery, semantic search, predictive intelligence, decision simulation, digital twin, generated business processes, autonomous governance, enterprise memory, data stewardship, personalized UX, natural-language enterprise programming, runtime security, continuous learning, executive intelligence, cross-system cognition, autonomous agents, and intent-driven enterprise computing.
Use when designing extensible Dataverse action packs, AI skills, workflow agents, industry modules, or reusable Dataverse skills. Produces marketplace architecture guidance only.
Use when planning dynamic task-specific forms, dashboards, tables, wizards, approval dialogs, or input masks generated for Dataverse and Power Apps scenarios. Produces UI plans only and generates no live UI.
Use when designing organizational memory for Dataverse AI actions, including user behavior, processes, preferences, common actions, approval patterns, and company language. Produces memory design guidance only.
| name | ai-safety-governance-layer |
| description | Use when reviewing Dataverse AI actions for permissions, policy validation, risk assessment, approval routing, auditability, and explainability. Produces governance guidance only; it does not enforce policies in a live tenant. |
Review proposed Dataverse and Power Platform AI actions before execution design is approved.
Use this skill for:
This skill provides governance analysis and design recommendations only. It must not claim that a live tenant policy has been checked or enforced.
Return:
Risk rating: low, medium, high, or blocked, with rationale.Required checks: permissions, policies, dependencies, and data quality validations.Approval path: who must approve and when.Simulation requirements: preview and impact details.Audit requirements: fields, evidence, and explanation text to store.Blocking issues: items that must be resolved before implementation.