querying-aws-s3

Queries S3 object metadata, tracks bucket activity, audits object changes, searches annotations, and analyzes storage metrics using S3 Metadata system tables (journal, inventory, annotation) and S3 Storage Lens tables via Athena SQL. Applies when counting objects, finding recent uploads or deletions, identifying who wrote to a prefix, breaking down storage classes, finding objects by tag, searching annotation content, analyzing storage lens metrics, or enabling S3 Metadata tracking. Prefers system tables over raw S3 APIs (list-objects-v2, head-object) at scale. Trigger phrases: bucket activity, object count, who uploaded, track deletions, storage class breakdown, find by tag, search annotations, storage lens metrics, audit bucket changes.

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

82%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 is highly actionable with executable SQL/CLI and a clear enable→query workflow supported by troubleshooting and security sections. It is efficient and well-structured, with only minor conciseness and feedback-loop gaps keeping it from full marks.

Suggestions

Add inline validate→fix→retry guidance next to each checkpoint (e.g., after 'Check If Configured' and 'Verify Permissions') instead of deferring all recovery to the Troubleshooting table.

Tighten the Overview's 'system tables are preferred over raw S3 APIs' rationale to a single bullet or move it to a short 'Why' note to trim explanation Claude largely infers.

Consider extracting the full least-privilege IAM policy and table catalog into a references/ file (e.g., SECURITY.md) to reduce SKILL.md length while keeping the overview pointer one level deep.

Dimension	Reasoning	Score
Conciseness	Largely lean — decision-tree table, troubleshooting table, and copy-paste SQL/CLI blocks earn their tokens — but the Overview's rationale for preferring system tables over raw APIs and a few explanatory sentences could be trimmed slightly. Not a 5 because minor over-explanation remains.	4 / 5
Actionability	Fully executable, copy-paste-ready AWS CLI and Athena SQL commands cover the common cases (enable, configure, query journal/inventory/annotation/Storage Lens), plus concrete IAM and encryption JSON policies.	5 / 5
Workflow Clarity	A clear numbered sequence (Check If Configured → Enable → Verify Permissions → Identify Target Table → Query) with TableStatus interpretation checkpoints and MUST/SHOULD constraints. Just shy of 5 because the validation feedback loop relies on the separate Troubleshooting table rather than inline validate→fix→retry steps at each checkpoint.	4 / 5
Progressive Disclosure	No bundle files exist, so all content lives in a single ~330-line SKILL.md; sections are well-organized with anchor navigation and external links out to AWS docs for deep schemas. Good structure and clearly signaled references, though the inline IAM policy and full table catalog could arguably be split into reference files.	4 / 5
	Total	17 / 20 Passed

Description

100%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 excellent: third-person voice, comprehensive concrete actions, explicit trigger phrases, and clear boundary guidance. It answers both 'what' and 'when' unambiguously.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Queries S3 object metadata, tracks bucket activity, audits object changes, searches annotations, and analyzes storage metrics' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers 'what' (five concrete actions over journal/inventory/annotation/Storage Lens tables via Athena) and 'when' ('Applies when counting objects, finding recent uploads or deletions...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicit 'Trigger phrases:' clause enumerates nine natural terms a user would actually say (bucket activity, object count, who uploaded, track deletions, storage class breakdown, find by tag, search annotations, storage lens metrics, audit bucket changes).	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (S3 Metadata system tables via Athena) with explicit boundary guidance ('Query data inside objects → No → querying-data-lake'), making conflict with adjacent skills minimal.	5 / 5
	Total	20 / 20 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: skills/specialized-skills/system-table-skills/querying-aws-s3/SKILL.md
Commit: d6ad2e4

Reviewed: about 2 hours 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.