CtrlK
BlogDocsLog inGet started
Tessl Logo

exploring-data-catalog

Full inventory and audit of AWS Glue Data Catalog assets across S3 Tables, Redshift-federated, and remote Iceberg catalogs. Triggers on: inventory the catalog, audit databases, list all tables, catalog overview, data landscape, enumerate catalogs, data inventory, search the catalog. Do NOT use for finding specific data (use finding-data-lake-assets), running queries (use querying-data-lake), or creating tables (use creating-data-lake-table).

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The content is highly actionable with executable commands, clear sequenced workflow and validation checkpoints, and well-structured progressive disclosure to a single real reference file. The main weakness is conciseness: the experimental catalog-context step is verbose with repeated constraint framing that could be trimmed or pushed to a reference.

Suggestions

Tighten Step 2 ('Consult Catalog Context'): move the detailed operations table and filter-clause JSON example into references/ and keep only the availability gate, opt-in prompt, and security notes inline.

Reduce repeated 'You MUST' constraint framing — consolidate the cross-cutting pagination and parameter-acquisition constraints once rather than restating them per step.

Consider moving the Argument Routing decision tree into the discovery-checklist reference so the SKILL.md body stays a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient and high-signal with no basic-concept padding, but Step 2's experimental catalog-context section (long embedded JSON filter example plus a multi-row operations table) and repeated 'You MUST' constraint framing add bulk that could be tightened or pushed to the reference. It sits above level 1 (no generic padding) but below level 3 (lean, every token earns its place).

2 / 3

Actionability

Provides fully executable aws glue / aws s3tables commands with real flags, a concrete ARN pattern, a filter-clause JSON example, and field-to-type classification tables — copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Five numbered, sequenced steps with explicit validation checkpoints (credential check, availability gate + user opt-in, ARN validation, pagination handling) and an error-to-fix troubleshooting table providing feedback loops, matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

The body is a clear overview that offloads the deep analysis framework to a real one-level-deep reference (references/discovery-checklist.md, confirmed present and not nested further), with well-signaled links and external doc URLs, matching the 'clear overview with well-signaled one-level-deep references' anchor.

3 / 3

Total

11

/

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 strong, well-targeted description: it names concrete actions and asset types, lists natural trigger terms, gives explicit when-to-use guidance, and disambiguates from sibling skills with negative triggers. No significant weaknesses; the only minor note is that some trigger terms are near-synonyms rather than maximally distinct user phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (inventory, audit, list) across three specific catalog subtypes (S3 Tables, Redshift-federated, remote Iceberg), matching the 'lists multiple specific concrete actions' anchor rather than the 'some actions, not comprehensive' level below.

3 / 3

Completeness

It explicitly answers what (full inventory/audit of Glue Data Catalog assets) and when (explicit 'Triggers on:' triggers plus negative 'Do NOT use for' guidance), satisfying the 'clearly answers both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

The 'Triggers on:' clause covers natural phrases a user would say ('list all tables', 'catalog overview', 'data landscape'), giving good coverage of natural terms; not level 2 since the term set is broad and user-idiomatic rather than missing common variations.

3 / 3

Distinctiveness Conflict Risk

Explicit negative triggers carve it apart from sibling skills ('Do NOT use for ... use finding-data-lake-assets / querying-data-lake / creating-data-lake-table'), giving it a clear niche unlikely to conflict.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.