finding-data-lake-assets

Resolve data lake and lakehouse asset references across Glue Data Catalog, S3, S3 Tables, and Redshift. Triggers on: find the table, where is our data, which table has, locate dataset, find data for, search catalog, what tables match, Redshift table, lakehouse table, data lake table, warehouse table, reverse lookup S3 path. Do NOT use for: full catalog audits (use exploring-data-catalog), running queries (use querying-data-lake), creating tables (use creating-data-lake-table).

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

A strong, actionable body with a well-sequenced validated workflow and concrete executable examples. Its main weaknesses are some repetition/verbosity in the experimental Step 2 section and a large inline API-reference-style block that would benefit from being split into its own reference file.

Suggestions

Move the Step 2 experimental Glue Discovery operations table and its repeated ARN examples into a dedicated reference file (e.g. references/glue-discovery.md), keeping SKILL.md as a concise overview that links to it.

Deduplicate the short-circuit criteria: state them once and have the security section reference them rather than re-listing the full conditions.

Tighten the repeated full-ARN placeholders (e.g. arn:aws:glue:<region>:<account>:table/<db>/<table>) by defining the pattern once and using a short form thereafter.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept filler, but Step 2 repeats the ARN pattern and short-circuit criteria across the operations table and the security section, and could be tightened; not quite the lean 3 anchor.	2 / 3
Actionability	Provides copy-paste-ready executable commands (aws glue search-tables, aws sts get-caller-identity), a complete boto3 paginator script, and concrete SQL queries with exact flags and output shapes.	3 / 3
Workflow Clarity	A clearly numbered Steps 1-7 sequence with explicit validation checkpoints (credential check, ARN pattern validation, availability-gate exit codes, confidence gate) and retry/backoff feedback; read-only ops so no destructive-cap applies.	3 / 3
Progressive Disclosure	There is a real, one-level-deep, clearly signaled reference (references/search-strategy.md) used for search patterns, but the large experimental Glue Discovery operations table in Step 2 is API-reference-style content kept inline that could be a separate 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 high-quality description: concrete actions, a rich set of natural trigger phrases, and explicit use/don't-use guidance that cleanly separates it from sibling skills. Third-person voice is maintained throughout with no over-claims.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("Resolve data lake and lakehouse asset references", "reverse lookup S3 path") across four specific services, matching the multiple-concrete-actions anchor rather than the single-domain 2 anchor.	3 / 3
Completeness	Explicitly answers what ("Resolve data lake and lakehouse asset references...") and when ("Triggers on:..." plus "Do NOT use for:..."), satisfying both halves of the 3 anchor.	3 / 3
Trigger Term Quality	Extensive natural phrasing a user would actually say ("find the table", "where is our data", "which table has", "locate dataset", "search catalog", "reverse lookup S3 path") with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Explicit "Do NOT use for" carve-outs naming sibling skills (exploring-data-catalog, querying-data-lake, creating-data-lake-table) give it a clear niche unlikely to trigger 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/finding-data-lake-assets/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.