CtrlK
BlogDocsLog inGet started
Tessl Logo

setting-up-cloudtrail-multi-region

Enables a multi-region AWS CloudTrail trail with S3 log storage, CloudWatch Logs integration, and CloudWatch Logs Insights queries for security monitoring and compliance auditing. Use when setting up centralized API activity logging across all AWS regions.

70

Quality

86%

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

72%

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

The body is well-structured and lean with excellent progressive disclosure, but its core actionability and workflow clarity are partial: the main setup procedure and its validation checkpoint live in the reference rather than the body, while concrete commands appear only in troubleshooting. Surfacing key executable steps and a validation checkpoint inline would raise the two 2-scored dimensions.

Suggestions

Add an inline validation checkpoint in the 'Set up a multi-region trail' section — e.g., run `aws cloudtrail get-trail-status --name <trail>` after creation and confirm `IsLogging` is true — so the body's workflow has an explicit feedback loop rather than relying on the reference.

Surface 2-3 key executable commands from the setup procedure inline (e.g., the create-trail and CloudWatch Logs role/resource-policy commands) instead of deferring all actionability to the reference, so the body is actionable on its own.

Tighten or repurpose the Overview paragraph, which largely restates the frontmatter description, to remove redundancy and recover a few tokens.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what CloudTrail is — and every section earns its place; the Overview's mild restatement of the description is a single short paragraph, staying at the lean-and-efficient anchor rather than the could-be-tightened level below.

3 / 3

Actionability

Troubleshooting supplies concrete commands ('aws sts get-caller-identity', 'start-logging'), but the core 'Set up' section defers all executable steps to the reference ('follow the procedure exactly. See [...]'), leaving the body's actionability incomplete rather than copy-paste ready. Not 1 because concrete guidance exists; not 3 because the main setup action is delegated away.

2 / 3

Workflow Clarity

Troubleshooting gives concrete error-recovery feedback, but the 'Set up' section shows no explicit numbered sequence or validation checkpoint in the body — the workflow and its checkpoints are implicit, deferred to the reference. Not 1 because a procedure pointer plus recovery steps exist; not 3 because the body lacks an explicit validation step in the setup flow.

2 / 3

Progressive Disclosure

A clear overview plus a well-signaled, one-level-deep reference — 'See [CloudTrail multi-region setup procedure](references/cloudtrail-multi-region-setup.md)' (verified to exist) — with content appropriately split between the procedure file and inline troubleshooting, matching the clear-overview-with-one-level-deep-references anchor.

3 / 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.

The description is strong across all dimensions: it states concrete capabilities in third person, includes natural trigger terms, and pairs an explicit 'Use when' clause with a distinct, well-scoped niche. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'multi-region AWS CloudTrail trail with S3 log storage, CloudWatch Logs integration, and CloudWatch Logs Insights queries' — in third person, matching the multiple-specific-actions anchor rather than the domain-plus-some-actions level below.

3 / 3

Completeness

Clearly answers what ('Enables a multi-region AWS CloudTrail trail...') and when via the explicit 'Use when setting up centralized API activity logging across all AWS regions' trigger clause, hitting both halves.

3 / 3

Trigger Term Quality

Covers natural terms an AWS user would actually say — 'CloudTrail', 'multi-region', 'CloudWatch Logs', 'security monitoring', 'compliance auditing', 'API activity logging' — with good coverage and no missing common variations.

3 / 3

Distinctiveness Conflict Risk

A clear niche — multi-region CloudTrail plus CloudWatch Logs/Insights integration for security and compliance — with distinct triggers unlikely to fire for unrelated skills.

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.