General business
AuraScore 81/100

Institutional Research Governance and Data Access Specification

Develop an end-to-end institutional data governance, ethics, and pipeline security specification for research consortia.

Use this template when designing formal data governance frameworks, role-based access architectures, and regulatory compliance standards across collaborative research initiatives. It turns abstract data ethics into enforceable technical specifications.

Template

Role: Senior Research Data Infrastructure Architect and Institutional Governance Lead with extensive multi-party research consortium experience.

Context

  • Highest data classification level: {{data_classification_tier}}
  • Participating consortium entities: {{research_consortium_partners}}
  • Mandatory data retention and sunset protocol: {{retention_protocol}}
  • Differential privacy and anonymization standard: {{anonymization_standard}}
  • Institutional Review Board (IRB) and governance mandate: {{governance_board_mandate}}
  • Target analytical compute and storage infrastructure: {{compute_infrastructure}}

Task

Produce an authoritative Research Data Governance and Pipeline Specification that defines access controls, de-identification mandates, audit trails, and data lifecycle management for multi-institutional collaboration.

Method

  1. Analyze the regulatory implications and data ingress perimeter for {{data_classification_tier}} across {{research_consortium_partners}}.
  2. Formalize mathematical and procedural criteria required to satisfy {{anonymization_standard}} prior to analytical release.
  3. Architect the Role-Based Access Control (RBAC) and attribute validation logic mapped directly to {{compute_infrastructure}}.
  4. Draft data lineage verification checkpoints spanning ingestion, transformation, sharing, and eventual purging under {{retention_protocol}}.
  5. Align access review workflows with the oversight parameters dictated by {{governance_board_mandate}}.
  6. Detail breach containment, credential revocation, and spill protocols for cross-institutional incidents.
  7. Specify validation testing criteria for cryptographic controls and air-gapped analytic enclaves.

Constraints

  • MUST define explicit quantitative thresholds for de-identification and re-identification risk under {{anonymization_standard}}.
  • MUST NOT leave data destruction or retention periods open to subjective interpretation.
  • Technical specifications must be strictly compatible with the limits of {{compute_infrastructure}}.
  • All consortium partners listed in {{research_consortium_partners}} must have defined role boundaries.

Output format

  1. Governance Scope and Scope Matrix (Max 200 words)
  2. Threat Model & Data Sensitivity Classification (Section 1.0)
  3. Anonymization & Transformation Pipeline Standards (Section 2.0 with mathematical thresholds)
  4. Access Control Architecture & RBAC Grid (Markdown Table: Role, Access Tier, Environment, Approval Requirement)
  5. Lifecycle, Retention, and Purge Protocol (Aligned to {{retention_protocol}})
  6. Incident Response and Audit Log Enforcement Specification

Self-review

  • Check that every requirement in {{governance_board_mandate}} has a corresponding enforcement mechanism in the RBAC grid.
  • Confirm that the anonymization standards match {{anonymization_standard}} mathematically and operationally.
  • Verify that compute access policies reflect the exact architecture constraints of {{compute_infrastructure}}.
AuraScore breakdown
81/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering12/12 · Strong

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

business-strategy
business-general
research-productivity-operations
research-ops
data-governance
security-spec