SkillVaultskills Browse all 500 skills

Data · Version 1.5.0 · Reviewed 2026-08-02

Data Contract Reviewer

Make data systems more correct and operable for schema-contract review and semantic definition with evidence, explicit trade-offs, and a verification plan.

4 method steps 5 documented failure modes 5 diagnostic checks 7 quality gates

Reviews producer-consumer data contracts for grain, semantics, nullability, freshness, quality rules, ownership, evolution, and incident response.

₹99 one-time

Get this skill archive

What this skill helps you do

  • Schema-contract review
  • Semantic definition
  • Evolution safety

How Data Contract Reviewer works

You provide

Obligations, data inventory, and current controls

It inspects

Requirement type and implemented control for schema-contract review

It decides

A semantic definition gap register with accountable owners

You verify

Each control mapped to evidence an auditor would accept

What it checks first

Data Contract Reviewer reviews producer-consumer data contracts for grain, semantics, nullability, freshness, quality rules, ownership, evolution, and incident response. Use it when the work involves Schema-contract review, Semantic definition, Evolution safety.

  1. Whether the obligation is a legal requirement, a contractual commitment, or an internal policy — the escalation path differs.
  2. The specific data categories and lawful basis, rather than a general statement about compliance.
  3. Data flows across jurisdictions and processors, which determine transfer obligations.
  4. Retention and deletion behavior in every downstream copy, including backups and analytics.
  5. Who is accountable for the decision, since a compliance analysis without an owner is not actionable.

Failure modes it recognizes

  • Deletion implemented in the primary store while copies persist in backups, exports, logs, and warehouses.
  • Consent collected for one purpose and reused for another without a valid basis.
  • A subprocessor added without a data-processing agreement or customer notification.
  • Retention policy defined but never enforced by an automated job.
  • A control documented in policy but not implemented in the system it describes.

Answers it will reject

  • Providing a definitive legal conclusion rather than a structured analysis for qualified review.
  • Treating a compliance certification as evidence that a specific control works.
  • Relying on contractual language to mitigate a technical risk that is technically preventable.
  • Presenting risk without severity, likelihood, and the accountable owner.

Decision rules it applies

  • Separate legal requirement, contractual obligation, and internal policy in every finding.
  • Escalate to qualified counsel for anything that constitutes legal advice, and say so plainly.
  • Map every obligation to a specific implemented control and its evidence, or mark it as a gap.
  • Prefer technical enforcement over documented intent, because documented intent is not a control.

Evidence it asks for

  • Build a data inventory: category, source, purpose, basis, location, retention, and downstream copies.
  • Trace one deletion request end to end and enumerate every store it must reach.
  • Record the evidence artifact that would satisfy an auditor for each control.

The method inside

  1. Map the artifact, actors, boundaries, and invariants relevant to schema-contract review.
  2. Trace concrete failure or abuse paths for semantic definition; do not report checklist items without a mechanism.
  3. Prioritize evolution safety findings by impact, likelihood, confidence, and cost of correction.
  4. Recommend the smallest defensible change, then define how an independent reviewer can verify it.

Deliverables

  • Schema-contract review assessment
  • Semantic definition decision and action plan
  • Evolution safety verification checklist

Evidence requirements

  • Schema, access patterns, query plans, or event contracts
  • Volume, cardinality, retention, and freshness
  • Consistency, latency, and migration constraints

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Review this customer metrics dataset before three teams build dashboards and models on top of it.

Expected output

The grain is undocumented and revenue mixes booked and collected amounts. Define one row per customer-day, name the financial semantic explicitly, add freshness and uniqueness expectations, and assign a producer owner...

Boundaries and compatibility

Ideal for

  • Schema-contract review: produce a decision or artifact grounded in supplied evidence.
  • Semantic definition: produce a decision or artifact grounded in supplied evidence.
  • Evolution safety: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Recommending indexes without a workload
  • Treating eventual consistency as universally acceptable

Agent compatibility

  • GitHub Copilot custom agents
  • Claude Agent Skills / SKILL.md
  • Any instruction-following chat model

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.