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

92%

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

85%

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

A well-organized triage overview that efficiently routes Clean Rooms failures to one-level-deep reference procedures with clear previews. Its main weakness is actionability: the body delegates all executable diagnostic detail to references, leaving no inline commands or first-line steps.

Suggestions

Add one or two inline first-line diagnostic commands (e.g., 'aws cleanrooms list-memberships --status ACTIVE --region <region>') so the body is directly actionable before delegating to a reference.

Include a brief disambiguation note for overlapping failure modes (e.g., when an error could be either IAM or KMS related) to make the triage routing more concrete.

Surface one inline validation checkpoint (e.g., 'confirm the membership ID resolves before proceeding') to strengthen workflow clarity within the body itself.

Dimension	Reasoning	Score
Conciseness	The body is lean (~20 lines) with no concept-explaining padding; each 'Covers ...' preview earns its place as routing help, assuming Claude's competence; not level 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	The body offers concrete routing — two explicit decision branches ('Access denied or permission error?', 'Missing CloudWatch logs ...?') each linking to a named reference with a coverage summary — but no executable commands or diagnostic steps inline, so key actionable detail sits one hop away in references; not level 1 because the guidance is precise rather than vague, not level 3 because nothing in the body is copy-paste executable.	2 / 3
Workflow Clarity	The triage workflow is a clear, unambiguous sequence (determine failure type → branch → route to the matching reference); per the simple-skills note a clear single-purpose decision tree can score 3, and the destructive/batch validation cap does not apply to read-only diagnostics; not level 2 because the sequence and branching are explicit rather than missing checkpoints for the body's scope.	3 / 3
Progressive Disclosure	The overview routes to two one-level-deep, real reference files (references/permission-debugging.md, references/custom-model-logging-debugging.md) with well-signaled link text and previews, while external doc links are segregated under 'Additional resources'; not level 2 because content is appropriately split and navigation is easy rather than poorly signaled.	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, third-person description that concisely states concrete capabilities across Clean Rooms subsystems and provides an explicit, natural-language trigger clause. It clearly answers both what the skill does and when to use it within a distinct niche.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and targets — 'Troubleshoots and debugs ... IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging ... custom ML model training and inference jobs' — matching the anchor for listing several specific concrete actions; not level 2 because the capability enumeration is comprehensive rather than partial.	3 / 3
Completeness	It explicitly answers both what ('Troubleshoots and debugs AWS Clean Rooms collaboration issues related to ...') and when ('Use when a customer reports ...'), matching the anchor for clear what-and-when with explicit triggers; not level 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	The 'Use when a customer reports permission failures, access errors, or log publishing issues in Clean Rooms' clause supplies natural terms a customer would actually say, giving good coverage; not level 2 because common reporting phrasings are well represented rather than missing variations.	3 / 3
Distinctiveness Conflict Risk	'AWS Clean Rooms' is a narrow, well-defined niche with triggers scoped to Clean Rooms-specific failure modes, making conflict with other skills unlikely; not level 2 because the domain and triggers are distinctly scoped rather than merely 'somewhat specific'.	3 / 3
	Total	12 / 12 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: 222ce56

Reviewed: 3 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.