querying-aws-sagemaker-catalog

Runs SQL analytics on SageMaker Catalog asset metadata tables exported as Apache Iceberg in S3 Tables. Covers governance queries, asset growth tracking, ownership audits, time-travel over catalog state, and metadata quality analysis. Applies when querying catalog inventory, finding assets without descriptions, comparing catalog snapshots, or auditing data ownership. Trigger phrases: catalog inventory SQL, how many assets, assets without descriptions, asset growth over time, who owns this data, catalog governance, data quality audit, catalog analytics.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and well-sequenced with executable commands, SQL examples, and a troubleshooting feedback table. It loses points for repeated snapshot_time emphasis and for keeping all reference-grade material inline rather than splitting it into a bundle file.

Suggestions

Consolidate the repeated 'always filter by snapshot_time' guidance into one prominent callout and reference it from the SQL examples to reduce token redundancy.

Move the full key-columns reference table and the six query examples into a references/queries.md file, keeping SKILL.md as an overview with one or two canonical examples.

Tighten the Overview paragraph, which restates the export mechanism already implied by the Decision Tree and Common Tasks sections.

Dimension	Reasoning	Score
Conciseness	The body is information-dense about a niche service, but the 'always filter by snapshot_time' warning is repeated across the constraints, key-columns table, examples, Key Behaviors, and Troubleshooting, and the Overview restates mechanisms covered elsewhere.	2 / 3
Actionability	Provides fully executable AWS CLI commands (datazone, s3tables, lakeformation, glue) and copy-paste-ready SQL queries with concrete table references and filters.	3 / 3
Workflow Clarity	A clear numbered sequence (check config → enable → verify permissions → query) with a pre-flight 'Check If Configured' checkpoint, explicit MUST constraints, and a Troubleshooting error/cause/fix table for feedback recovery.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but it is a >200-line monolithic file with no bundle references; the six SQL examples and full key-columns reference table could appropriately live in a one-level-deep reference file.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that covers concrete capabilities, natural trigger phrases, explicit use-when guidance, and a distinct niche. It is concise without padding or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'governance queries, asset growth tracking, ownership audits, time-travel over catalog state, and metadata quality analysis' — rather than vague language.	3 / 3
Completeness	Clearly states what it does (SQL analytics on SageMaker Catalog Iceberg tables) and when to use it via an explicit 'Applies when...' clause with concrete triggers.	3 / 3
Trigger Term Quality	Trigger phrases like 'how many assets', 'who owns this data', and 'assets without descriptions' are natural terms a user would say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The SageMaker Catalog / S3 Tables / Iceberg niche is specific and the triggers (catalog inventory SQL, catalog governance) are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/system-table-skills/querying-aws-sagemaker-catalog/SKILL.md
Commit: 222ce56

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.