CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

84%

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

The canonical home for this skill is setting-up-cloudtrail-multi-region in aws/agent-toolkit-for-aws

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 efficient and well-structured with exemplary progressive disclosure and concrete troubleshooting commands, but the core workflow's sequence and validation checkpoints are entirely outsourced to the reference with no inline summary, and the Overview duplicates the frontmatter description. Weak spots are workflow visibility and a small redundancy.

Suggestions

Add a brief inline skeleton of the setup sequence in the body (e.g., 1. Create S3 bucket → 2. Create log group → 3. Create IAM role → 4. Enable multi-region trail → 5. Verify configuration) so the workflow shape and the existence of the verification step are visible before opening the reference.

Trim or repurpose the Overview paragraph, which restates the frontmatter description almost verbatim ("Domain expertise for enabling AWS CloudTrail across all regions... for security monitoring, compliance auditing, and operational analysis"), saving tokens without losing information.

Surface the validation checkpoint explicitly, e.g., a one-line note such as "After creating the trail, confirm logging is active before considering the setup complete" (the reference's step 8 does this, but the body never mentions it).

DimensionReasoningScore

Conciseness

The body is lean with no concept explanations and terse, command-bearing troubleshooting entries ("Verify your identity with `aws sts get-caller-identity`"), but the Overview paragraph ("Domain expertise for enabling AWS CloudTrail across all regions...") restates the frontmatter description nearly verbatim and could be trimmed. Matches 4 (minor trimmable redundancy), not 5 (not every token earns its place).

4 / 5

Actionability

Troubleshooting provides concrete, executable commands (`aws sts get-caller-identity`, `start-logging`, the "Do NOT use `*FullAccess` managed policies" warning, 5-15 minute timing guidance), and the setup task is delegated via a clear pointer to a real 332-line procedure. Minor gap: no inline quick-start command for the primary setup task itself. Matches 4, not 5 (copy-paste-ready coverage of common cases is only achieved via the reference, not in the body).

4 / 5

Workflow Clarity

The multi-step setup sequence and its verification steps ("Verify Configuration", "Generate Setup Report") live entirely in the referenced procedure; the body shows no sequence, no inline checkpoints, and does not signal that the procedure includes validation. Matches 3 (sequence/checkpoints implicit rather than present); not 4 because the body itself displays no step sequence at all. Provisioning AWS resources is not destructive/batch, so the validation cap does not apply.

3 / 5

Progressive Disclosure

The ~46-line body keeps only an overview, a clearly signaled one-level-deep reference link ([CloudTrail multi-region setup procedure](references/cloudtrail-multi-region-setup.md) — verified to exist, 332 lines, no nested references), and an inline troubleshooting digest, while the bulk procedure is appropriately split into the reference file. Matches the 5 anchor (clear overview, well-signaled one-level-deep references, easy navigation).

5 / 5

Total

16

/

20

Passed

Description

92%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.

A strong description: third-person, specific, and comprehensive on the "what", with an explicit and concrete "Use when" clause. The only weakness is modest synonym coverage in trigger terms (e.g., "audit logging", "activity history").

DimensionReasoningScore

Specificity

"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" lists multiple specific concrete actions with comprehensive domain coverage, in proper third-person voice. This matches the 5 anchor (multiple specific actions, comprehensive coverage); it is not 4 because there are no minor gaps in the action inventory.

5 / 5

Completeness

The description explicitly answers both "what" (enables a multi-region trail with S3 storage, CloudWatch Logs integration, and Insights queries) and "when" ("Use when setting up centralized API activity logging across all AWS regions") with concrete trigger context. This matches the 5 anchor exactly; not 4 because the "when" clause is already explicit and concrete.

5 / 5

Trigger Term Quality

Natural keywords are present ("multi-region", "AWS CloudTrail", "S3", "CloudWatch", "compliance auditing", "centralized API activity logging"), matching "good keyword coverage; a few natural terms missing". Not 5: common user phrasings like "audit logging", "activity history", or "set up a trail" variants are absent.

4 / 5

Distinctiveness Conflict Risk

"Multi-region AWS CloudTrail trail" with CloudWatch Logs integration carves a clear niche with distinct triggers (CloudTrail setup, centralized API activity logging) and minimal overlap with generic S3/CloudWatch/monitoring skills. Matches the 5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

mreferre/aws-agent-toolkit-skills

Path

.kiro/skills/setting-up-cloudtrail-multi-region/SKILL.md

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.