AI Data Readiness Triage

AI Data Readiness Triage

Mission

Assess whether a dataset or data domain is ready for AI, analytics, or modeling before a project commits time and budget.

Current pain point: AI projects stall because access, freshness, quality, lineage, privacy, labels, and ownership are discovered too late.

Why this skill exists: Readiness scoring gives leaders a hard go, fix-first, or stop decision instead of optimistic prototype theater.

Operating Rules

• Start by restating the decision this skill is supporting.
• Inspect local artifacts first before asking for context.
• Treat scripts as evidence collectors, not as substitutes for judgment.
• Preserve raw data, notebooks, configs, and model artifacts unless the user explicitly asks for mutation.
• Mark missing context as unknown, not provided, or owner decision; do not invent it.
• Classify each blocker as stop, fix-first, monitor, accepted risk, or owner decision.
• Use the output contract exactly unless the user asks for a different format.
• Keep final recommendations auditable: every important claim needs evidence, assumption, or caveat.

What This Skill Must Do

• Transform a vague request into an explicit AI Data Readiness Triage decision with named owner, evidence, assumptions, and action threshold.
• Inspect local artifacts first: data extracts, schemas, notebooks, SQL, pipeline configs, model reports, tickets, and prior decisions.
• Separate mechanical checks from expert judgment so another reviewer can reproduce what was checked and what was inferred.
• Classify findings as stop, fix-first, monitor, accepted risk, or owner decision instead of producing generic advice.
• Preserve raw evidence and never silently mutate data, notebooks, model artifacts, or production configs.
• Return a decision artifact that can be handed to a data scientist, ML engineer, governance reviewer, or stakeholder without hidden context.

Required Inputs

• dataset paths or schemas
• data owner
• intended use case
• privacy or compliance constraints
• label or ground-truth plan

If an input is missing, inspect available files first. Ask only for information that cannot be recovered from the workspace and would change the recommendation.

Workflow

1. Inventory access, ownership, lineage, refresh cadence, privacy, and retention constraints.
2. Profile quality, missingness, duplication, outliers, type drift, and label coverage.
3. Score readiness across governance, quality, representativeness, reproducibility, and operational fit.
4. Classify blockers as stop, fix-first, monitor, or accepted risk.
5. Return a readiness scorecard with the smallest credible next action.

Red Flags

• unknown owner
• no label source
• PII without approved use
• high missingness in core fields
• freshness mismatched to decision cycle

When a red flag appears, slow down and surface it in Risks. A red flag does not always mean stop, but it must change the recommendation or the confidence level.

Resources

• Read references/playbook.md for the skill-specific checklist, scoring rubric, and failure modes.
• Read references/acceptance-tests.md before forward-testing clean, messy, and adversarial requests.
• Read references/agent-portability.md when adapting this skill to Claude, Gemini, Copilot, Cursor, Windsurf, Gravity, LangGraph, CrewAI, AutoGen, or local agents.
• Read references/quality-rubric.md when reviewing whether the output meets senior data-science standards.
• Use scripts/quick_validate_skill.py . --strict before publishing or installing the skill.

Use only the specific reference file needed for the task; keep context small.

Output Contract

Return these sections unless the user requests another format:

• Problem: the decision, artifact, model, data source, or workflow being handled.
• Inputs: files, data, stakeholder context, assumptions, and missing context used.
• Checks performed: concrete inspections, scripts, and reasoning checks.
• Findings: prioritized observations with evidence.
• Decision: go, fix-first, stop, proceed-with-risk, or needs-owner-review.
• Risks: unresolved blockers, caveats, and owner decisions.
• Next actions: smallest useful follow-up steps.
• Artifacts: generated files, specs, reports, scripts, or links.

Final Checks

• Did the response answer the actual decision, not just analyze data?
• Did it preserve evidence and avoid silent mutation?
• Did it name unknowns and owner decisions?
• Did it include at least one concrete next action?
• Did it avoid overclaiming causality, readiness, compliance, or production safety?