CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

87%

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 aws-cleanrooms in aws/agent-toolkit-for-aws

SKILL.md
Quality
Evals
Security

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.

An exemplary progressive-disclosure router: the SKILL.md body stays lean, dispatches by symptom to well-structured one-level-deep reference procedures, and avoids teaching anything Claude already knows. The only gaps are minor: the body could add a fallback branch for unclassified failure types and brief upfront guidance (e.g., which parameters to gather) so routing works without first opening a reference file.

DimensionReasoningScore

Conciseness

The ~30-line body is pure routing: no explanations of concepts Claude already knows, no padding, and every line directs action. The per-reference coverage summaries ("Covers IAM role policies (inline + attached managed), S3 bucket policies...") function as navigation signals rather than duplicated content, matching anchor 5's 'every token earns its place'.

5 / 5

Actionability

Concrete decision guidance ("Access denied or permission error? → See [permission debugging procedure](references/permission-debugging.md)") routes each symptom to a specific executable procedure, but the body itself contains no commands, parameter-gathering, or verification steps — those live entirely in the reference files. Fits anchor 4 (mostly executable guidance, minor gaps) better than 5.

4 / 5

Workflow Clarity

The workflow ("Determine the failure type" then two symptom-keyed branches) is clear and unambiguous for the covered cases, and the referenced procedures contain validation steps. Not 5 because there is no fallback guidance for failure types outside the two branches (e.g., an issue that is neither an access error nor a logging problem).

4 / 5

Progressive Disclosure

The body is a lean overview with two clearly signaled references that are exactly one level deep (verified against the actual bundle: both files exist, are substantive, and contain only external AWS doc links, no nested .md references), plus a separate external-resources section. Matches anchor 5; not 4, since navigation is unambiguous and content is appropriately split.

5 / 5

Total

18

/

20

Passed

Description

87%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 that clearly states what the skill does and when to use it, with concrete trigger phrasing and a well-scoped niche. Minor room for improvement: broaden trigger synonyms (e.g., "access denied", "not authorized") and enumerate more distinct action verbs.

DimensionReasoningScore

Specificity

The description names the domain and specific issue areas comprehensively ("IAM roles, S3 bucket policies, KMS keys, Lake Formation permissions, and CloudWatch logging"), but the action verbs are limited to two near-synonyms ("Troubleshoots and debugs"), falling just short of anchor 5's multiple distinct concrete actions.

4 / 5

Completeness

It clearly answers what ("Troubleshoots and debugs AWS Clean Rooms collaboration issues related to...") and explicitly answers when with concrete trigger phrases ("Use when a customer reports permission failures, access errors, or log publishing issues in Clean Rooms"), matching anchor 5. Not 4, because the 'when' clause is explicit and specific rather than improvable.

5 / 5

Trigger Term Quality

"permission failures, access errors, or log publishing issues" are natural phrases a user would report, giving good keyword coverage, but common variations like "access denied", "not authorized", or specific error messages are missing. Fits anchor 4 better than 3 (coverage is genuinely good, not just 'some relevant keywords') and better than 5 (synonym coverage is incomplete).

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (AWS Clean Rooms) with service-specific triggers scoped by "in Clean Rooms", giving minimal conflict risk with broader AWS IAM/S3 debugging skills. Matches anchor 5; not 4, since the trigger clause explicitly scopes activation to this service.

5 / 5

Total

18

/

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/aws-cleanrooms/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.