# Dataset Source Assess

> Plan and review a bounded, non-mutating dataset source check and redacted preview.

- Skill: `jmagly/dataset-source-assess` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jmagly/dataset-source-assess`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jmagly/dataset-source-assess/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: jmagly (https://skillmd.com/u/jmagly)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/jmagly/dataset-source-assess

---


# Dataset Source Assessment

Consume a registered source reference. Propose `aiwg dataset check <source-id> --json`
and `aiwg dataset preview <source-id> --json`; these operations must remain bounded,
side-effect free, and redacted. Explain adapter/version, schema binding, identity
and revision strategy, incremental cursor support, locality/network behavior,
and evidence-backed maturity.

Never inspect credential or environment values. Distinguish absent, stale,
unverified, unsupported, and degraded capability states. Emit an assessment
reference for `dataset-capability-recommend`.