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

92%

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%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 highly actionable, well-sequenced workflow with executable AWS CLI commands, explicit validation and STOP conditions, and clean one-level-deep progressive disclosure into four real reference files. The only weakness is mild token redundancy from repeated 'You MUST' constraint phrasing and duplicated naming rules.

Suggestions

Consolidate the repeated lowercase/no-hyphen naming rule into a single constraint (Step 2) and drop the duplicate in Step 4 to save tokens.

Trim boilerplate 'You MUST' framing where a plain imperative would carry the same weight (e.g., 'Check existing buckets with aws s3tables list-table-buckets'), keeping MUST only for genuine hard requirements.

Dimension	Reasoning	Score
Conciseness	The body is efficient — decision tables, commands, and constraint bullets with no concept explanations Claude already knows — but the repeated 'You MUST' framing and duplicated rules (lowercase/no-hyphen naming appears in both Step 2 and Step 4) could be trimmed. Not 5: there is noticeable redundancy; not 3: padding is minor, not whole unnecessary sections.	4 / 5
Actionability	Copy-paste-ready commands throughout: 'aws s3tables create-table-bucket --name <BUCKET_NAME> --region <REGION>', the complete 'aws glue create-catalog' JSON payload, and a full metadata JSON example including a partitionSpec. Not 4: the common cases (default S3 Tables API path, Glue catalog setup, access control) are all covered with executable specifics.	5 / 5
Workflow Clarity	Steps 1-8 are clearly sequenced, preceded by a decision-guide table with explicit STOP conditions, ending in verification ('You MUST verify with aws s3tables get-table' plus Athena DESCRIBE with the exact query-execution-context), with a troubleshooting table for error recovery. Not 4: validation checkpoints and error-recovery guidance are explicit, not merely present.	5 / 5
Progressive Disclosure	The body is a well-sectioned overview that points to four real, one-level-deep reference files (all present in references/), signaled both inline at point of need ('You MUST read references/best-practices.md for Iceberg type mapping') and in a described 'Additional Resources' list. Not 4: navigation is clear and the split is appropriate with no buried or nested references.	5 / 5
	Total	19 / 20 Passed

Description

92%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 strong description: concrete capability list, explicit trigger phrases, and explicit de-confliction with four sibling skills in third-person voice. The only weakness is a trigger list with a couple of generic or missing natural terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Sets up table bucket, namespace, table, schema, Glue catalog registration, partitioning, IAM access control' — giving comprehensive coverage of the skill's capabilities in third-person voice. Not 4: there are no minor gaps in the action coverage.	5 / 5
Completeness	Explicitly answers both what ('Create managed Iceberg tables... Sets up table bucket, namespace, table, schema, Glue catalog registration...') and when ('Triggers on: create table, data lake table, ...') with concrete trigger phrases. Not 4: the 'when' clause is fully explicit, not merely present.	5 / 5
Trigger Term Quality	Good keyword coverage with synonyms ('create table', 'data lake table', 'analytics table', 'S3 Tables', 'Iceberg', 'Athena table'), but natural phrases like 'table bucket' or 'create a table in Athena' are missing and 'structured data storage' is generic. Not 5: coverage is not fully comprehensive; not 3: the synonym set is much richer than a single domain keyword.	4 / 5
Distinctiveness Conflict Risk	Clear niche (managed Iceberg tables via S3 Tables) with explicit negative boundary guidance routing four adjacent tasks to named sibling skills ('Do NOT use for: importing files (use ingesting-into-data-lake)...'). Not 4: conflict risk is minimal because de-confliction is explicit, not just implied by specificity.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: aws/agent-toolkit-for-aws
Path: plugins/aws-data-analytics/skills/creating-data-lake-table/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.