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

91%

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

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.

The body delivers highly actionable, executable guidance with a well-sequenced, validated workflow and a working external reference. Its main weakness is conciseness: the experimental catalog-context section is verbose for an opt-in path, and some of that detail could live in a separate reference file.

Suggestions

Move the experimental Glue Discovery (SearchAssets/GetAsset/IterableForms) operations table and examples into a dedicated references file, leaving Step 2 as a short gating + pointer section to improve both conciseness and progressive_disclosure.

Tighten the security prose in Step 2 by consolidating the four bolded rules into a compact checklist; the repeated 'MUST NOT' framing can be condensed without losing the untrusted-data guidance.

Consider a one-line 'When to use which layer' summary near Step 5 so the reader can pick a layer without re-reading each layer's full block.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean operational detail (real CLI flags, response schemas, filter clauses, a full boto3 script) that earns its tokens, but the experimental Step 2 catalog-context section runs long for an opt-in, availability-gated path and could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: aws glue search-assets/get-asset/list-iterable-forms/batch-get-iterable-forms, s3api and s3tables commands, SQL queries, and a complete boto3 paginator script with real arguments and example values.	5 / 5
Workflow Clarity	Steps 1-7 are clearly sequenced with explicit validation checkpoints (credential check, availability gate, user opt-in, confidence gate, stop-early conditions) plus a troubleshooting error-cause-fix table providing feedback loops for recovery.	5 / 5
Progressive Disclosure	Clear section structure with a real one-level-deep reference (references/search-strategy.md, linked and verified present) and an Additional Resources section, but the large experimental catalog-context API table is inlined rather than split into a reference file, a minor organization gap below a 5.	4 / 5
	Total	18 / 20 Passed

Description

95%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.

The description is tightly written in third person, with a concrete what, a rich natural-language trigger list, and explicit negative boundaries that distinguish it from sibling skills. Its only slight weakness is that the capability is conveyed through a single resolve verb rather than an enumerated action set.

Dimension	Reasoning	Score
Specificity	Names the concrete action ("Resolve data lake and lakehouse asset references") and the four target systems (Glue Data Catalog, S3, S3 Tables, Redshift) plus reverse lookup, but the action set is essentially a single resolve verb rather than multiple distinct operations, leaving a minor coverage gap below a 5.	4 / 5
Completeness	Explicitly states what (resolve asset references across four named stores) and when (a concrete "Triggers on:" phrase list), and adds a "Do NOT use for" boundary clause, satisfying both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Comprehensive natural-phrase trigger list ("find the table", "where is our data", "which table has", "locate dataset", "reverse lookup S3 path") plus synonyms (lakehouse table, data lake table, warehouse table) covering how users actually phrase these requests.	5 / 5
Distinctiveness Conflict Risk	A clear resolver niche with distinct triggers and an explicit negative-boundary list routing audits, queries, and table creation to sibling skills, minimizing the chance of triggering the wrong skill.	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/finding-data-lake-assets/SKILL.md
Commit: 8ea26bd

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.