creating-data-lake-table

Create managed Iceberg tables using Amazon S3 Tables (s3tables API namespace) with automatic compaction and snapshot management. Sets up table bucket, namespace, table, schema, Glue catalog registration, partitioning, IAM access control. Triggers on: create table, data lake table, analytics table, structured data storage, S3 Tables, Iceberg, Athena table, partitioning strategy, access permissions. Do NOT use for: importing files (use ingesting-into-data-lake), vector storage (use storing-and-querying-vectors), querying existing tables (use querying-data-lake), or locating existing table (use finding-data-lake-assets).

Quality

96%

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

92%

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

The body is a strong, actionable runbook: executable commands, a clear sequenced workflow with validation checkpoints, and well-structured progressive disclosure into real reference files. The only minor weakness is conciseness — some repeated constraints and an inline catalog-creation JSON block could be tightened or moved to a reference.

Suggestions

Dedupe the recurring 'You MUST use lowercase names with no hyphens' and credential-check constraints into a single Constraints section referenced where needed to trim repetition.

Move the verbose aws glue create-catalog JSON block into best-practices.md or a dedicated reference and link to it, keeping the inline example lean.

Consolidate the per-step 'Constraints' blocks where they repeat IAM/region guidance to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation fluff (no 'what is a data lake' padding), but several constraints are restated across sections and the full inline Glue create-catalog JSON is bulk that could live in a reference, keeping it just shy of 'every token earns its place'.	2.5 / 3
Actionability	Provides fully executable aws s3tables/aws glue commands with real flags and placeholders, a complete nested metadata JSON example, and a concrete error/cause/fix table — copy-paste ready guidance.	3 / 3
Workflow Clarity	An explicit numbered 1-8 sequence is fronted by a decision table and backed by MUST checkpoints; the destructive/batch operations include verification (Step 8 verify, 'You MUST check existing') and a troubleshooting feedback loop.	3 / 3
Progressive Disclosure	A concise overview points to four one-level-deep, well-signaled references (all verified to exist: best-practices.md, athena-ddl-path.md, table-creation-glue-etl.md, access-control.md), with an Additional Resources index, and the body keeps detail appropriately scoped rather than monolithic.	3 / 3
	Total	11.5 / 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.

The description is specific, comprehensive, and distinctive: it lists concrete setup actions, provides natural trigger terms, answers both what and when, and explicitly disambiguates from sibling skills. It is well above the good-example anchors and shows no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Sets up table bucket, namespace, table, schema, Glue catalog registration, partitioning, IAM access control' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what it does ('Create managed Iceberg tables...') and when to use it ('Triggers on: ...'), with an explicit 'Use when' equivalent trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	'Triggers on: create table, data lake table, analytics table, structured data storage, S3 Tables, Iceberg, Athena table, partitioning strategy, access permissions' gives good coverage of natural terms users would say.	3 / 3
Distinctiveness Conflict Risk	Clear S3 Tables/Iceberg niche plus an explicit 'Do NOT use for' clause redirecting to ingesting-into-data-lake, storing-and-querying-vectors, querying-data-lake, and finding-data-lake-assets makes it unlikely to trigger for the wrong skill.	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: plugins/aws-data-analytics/skills/creating-data-lake-table/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.