aws-cleanrooms

Troubleshoots and debugs AWS Clean Rooms collaboration issues related to IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging for custom ML model training and inference jobs. Use when a customer reports permission failures, access errors, or log publishing issues in Clean Rooms.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 an exemplary router: lean, correctly structured for progressive disclosure, and both reference links resolve to real one-level-deep procedure files. Its only gaps are the absence of any inline diagnostic quick-checks (e.g., a first AWS CLI command to run) and no fallback path when the reported error matches neither branch.

Suggestions

Add a brief fallback line for errors that match neither branch (e.g., where to look for Clean Rooms error codes or when to consult the AWS service docs links).

Include one inline quick-check command (e.g., a CloudWatch Logs Insights orsts simulate-custom-policy call) so the model can gather the first diagnostic datum without opening a reference file.

Add a third branch or note covering collaboration configuration/analysis errors if the skill is meant to cover more than permission and logging failures.

Dimension	Reasoning	Score
Conciseness	The body is ~30 lean lines with zero concept re-teaching: the Overview is one sentence and each branch's "Covers..." preview carries routing information rather than padding, so every token earns its place.	5 / 5
Actionability	"Determine the failure type: Access denied or permission error? → See [permission debugging procedure](references/permission-debugging.md)" is a concrete, executable triage decision with pointers to real procedure files, but the body itself contains no commands, CLI invocations, or examples — those all live in the references — leaving minor gaps.	4 / 5
Workflow Clarity	The two-branch dispatch (permission error vs. missing CloudWatch logs) is clearly sequenced and unambiguous for the covered cases, but there is no fallback guidance for errors matching neither branch; not a destructive or batch operation, so no cap applies.	4 / 5
Progressive Disclosure	Both bundle files (references/permission-debugging.md and references/custom-model-logging-debugging.md) exist, are linked with descriptive previews of what each covers, and contain no nested references — a clear overview with well-signaled, one-level-deep references.	5 / 5
	Total	18 / 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: it states concrete troubleshooting actions, enumerates the exact AWS permission surfaces covered, and provides an explicit 'Use when' clause with natural trigger phrases. The only weakness is that a few common user phrasings (e.g., 'access denied', 'logs not showing up') are absent as trigger synonyms.

Suggestions

Add common user-side trigger variations such as 'access denied' or 'logs missing/not publishing' to the 'Use when' clause to broaden natural-term coverage.

Consider mentioning the .pptx-equivalent natural shorthand for the domain (e.g., 'Clean Rooms collaboration setup or custom ML model jobs') so users describing setup rather than failure also match.

Dimension	Reasoning	Score
Specificity	"Troubleshoots and debugs AWS Clean Rooms collaboration issues related to IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging" names concrete actions and comprehensively enumerates the specific permission surfaces involved, matching the 5 anchor; it is not 4 because coverage of the domain shows no real gaps.	5 / 5
Completeness	Both parts are explicit: the what ("Troubleshoots and debugs AWS Clean Rooms collaboration issues related to IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging") and the when ("Use when a customer reports permission failures, access errors, or log publishing issues in Clean Rooms") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"permission failures, access errors, or log publishing issues" are natural phrases a user would say, giving good keyword coverage, but common variations like "access denied" or "can't see logs" are missing, fitting the 4 anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	AWS Clean Rooms with its specific service dependencies (Configured ML model jobs, Lake Formation, Clean Rooms service roles) is a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 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/analytics-skills/aws-cleanrooms/SKILL.md
Commit: b8171ad

Reviewed: 5 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.