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

94%

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

88%Weight 40%Scale 1-5

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

A strong operational reference: fully executable commands and queries, a decision tree that routes to alternative skills, validation checkpoints, and thorough error-recovery guidance. The only weaknesses are mild internal repetition and a monolithic single-file structure where a references/ split would improve token efficiency.

Suggestions

State the snapshot_time filter rule once (e.g., in Constraints) and have the Key Behaviors and Troubleshooting sections reference it rather than restating it, trimming ~3 redundant lines.

Move the six SQL examples and the key-columns table into a references/queries.md file, keeping 1-2 quick-start examples inline in SKILL.md with clearly signaled one-level-deep links.

Consolidate the encryption guidance (currently split between the Enable section's note and Security Considerations) into the Security section to avoid duplicated advice.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific with no filler explanation of concepts Claude already knows, but key rules are repeated — 'Always filter by snapshot_time' appears in Constraints, the Key columns table, and Key Behaviors, and the encryption-cannot-change note appears in both section 2 and Security Considerations.	4 / 5
Actionability	Everything is copy-paste executable: complete AWS CLI commands with placeholders ('aws datazone put-data-export-configuration ... --enable-export'), the exact three-part Iceberg query path, and six ready-to-run SQL examples covering the common cases named in the description.	5 / 5
Workflow Clarity	Common Tasks are sequenced (Check If Configured → Enable → Verify Permissions → Query) with explicit validation checkpoints (bucket-existence check, Lake Formation grant verification, 'MUST confirm workgroup and output location before executing') and a Troubleshooting table mapping each error to a cause and fix, giving clear error-recovery feedback loops. Queries are read-only, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	Well-organized sections (Overview, Decision Tree, Common Tasks, Key Behaviors, Troubleshooting, Security, Additional Resources) with clear external AWS doc links, but the skill is a single ~225-line file with no bundle — the SQL example library and key-columns schema are natural candidates for references/ files that would keep SKILL.md as a leaner overview.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 model description: concrete third-person capability list, explicit use-when guidance, and natural trigger phrases that comprehensively cover the catalog-analytics domain. No vague language, padding, or over-claims.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities — 'Runs SQL analytics on SageMaker Catalog asset metadata tables', 'governance queries, asset growth tracking, ownership audits, time-travel over catalog state, and metadata quality analysis' — comprehensively covering the skill's scope in third-person voice.	5 / 5
Completeness	It explicitly answers both 'what' (SQL analytics on Iceberg-exported catalog metadata, with five named capability areas) and 'when' (an 'Applies when...' clause plus a dedicated trigger-phrase list), matching the top anchor exactly.	5 / 5
Trigger Term Quality	Beyond the 'Applies when' clause ('querying catalog inventory, finding assets without descriptions, comparing catalog snapshots, or auditing data ownership'), it adds natural trigger phrases users would actually say: 'how many assets', 'who owns this data', 'asset growth over time', 'catalog governance'.	5 / 5
Distinctiveness Conflict Risk	The SageMaker Catalog / S3 Tables / Iceberg metadata niche is clearly distinct with dedicated trigger phrases, so risk of firing for a generic SQL or data-lake skill is minimal; the body's decision tree further separates adjacent skills.	5 / 5
	Total	20 / 20 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: b8171ad

Reviewed: 5 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.