CtrlK
BlogDocsLog inGet started
Tessl Logo

exporting-rds-to-s3

Exports Amazon RDS or Aurora database snapshots to Amazon S3 in Apache Parquet format for analytics, backup, or data migration. Handles snapshot selection or creation, IAM role setup, KMS encryption, S3 bucket preparation, export task execution, progress monitoring, and data verification. Use when exporting RDS/Aurora data to S3 for Athena, Glue, or Redshift Spectrum consumption.

68

Quality

82%

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%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.

A well-structured, token-efficient overview that uses progressive disclosure correctly: quick actionable troubleshooting inline and a complete procedure one reference away. The main weakness is that the body itself carries no validation checkpoints for the multi-step export workflow, and the Overview duplicates the frontmatter description.

Suggestions

Add brief validation checkpoints to the export workflow section (e.g., 'confirm snapshot status is available before initiating the export' and 'verify Parquet files exist in S3 before reporting success') so the body alone conveys where to stop and check, rather than relying entirely on the reference file.

Replace the Overview paragraph, which restates the frontmatter description nearly verbatim, with a one-sentence purpose line or drop it entirely to save tokens.

Name the key required inputs (database identifier, region, S3 bucket/prefix, export type) inline before linking to the procedure, so the delegation to the reference is actionable without a second read.

DimensionReasoningScore

Conciseness

The body is efficient — troubleshooting items state only non-obvious facts (engine support matrix, confused-deputy conditions, IAM propagation delay) — but the Overview paragraph restates the frontmatter description nearly verbatim ('snapshot identification or creation, IAM role and KMS encryption setup, S3 bucket preparation, export task initiation, progress monitoring, data verification'), which could be trimmed. It is not a 5 because of that redundancy; not a 3 because there is no padding or explanation of concepts Claude already knows.

4 / 5

Actionability

Concrete, executable guidance is present: specific CLI commands ('use describe-db-clusters instead of describe-db-instances'), exact trust-policy conditions ('aws:SourceAccount and aws:SourceArn'), and a timing constant ('Wait 10-15 seconds after role creation'), plus a pointer to the complete procedure file. It is not a 5 because the main workflow section itself contains no commands or parameters — executability is delegated to the reference; not a 3 because the inline guidance that does exist is specific and correct, and the delegation target is real and complete.

4 / 5

Workflow Clarity

The phase sequence is present via the Overview list ('snapshot identification or creation, IAM role and KMS encryption setup, S3 bucket preparation, export task initiation, progress monitoring, data verification') and the procedure reference contains explicit verification steps, but the body itself has no validation checkpoints — it says only 'follow the procedure exactly' and defers everything else. This matches the score-3 anchor (sequence present, checkpoints missing or implicit); it is not a 4 because a reader of the body alone cannot tell where to stop and validate before proceeding with this batch data operation.

3 / 5

Progressive Disclosure

The body is a lean overview with a single one-level-deep reference (references/export-rds-to-s3.md) that exists in the bundle and is clearly signaled twice as a markdown link. Content is appropriately split: quick troubleshooting fixes inline, full procedure and detail in the reference. This matches the score-5 anchor; the score-4 anchor's 'minor organization gaps' do not apply since navigation is unambiguous.

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: concrete and comprehensive on capabilities, explicit 'Use when...' trigger guidance, third-person voice, and a well-delineated AWS niche. Only minor trigger-synonym gaps keep it from full marks.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'snapshot selection or creation, IAM role setup, KMS encryption, S3 bucket preparation, export task execution, progress monitoring, and data verification' — covering the workflow comprehensively, matching the score-5 anchor. It is not a 4 because coverage of the domain's actions is complete rather than having minor gaps.

5 / 5

Completeness

Explicitly answers both questions: the 'what' is the full action list ('Exports... Handles snapshot selection or creation... data verification') and the 'when' is the concrete trigger clause 'Use when exporting RDS/Aurora data to S3 for Athena, Glue, or Redshift Spectrum consumption.' This matches the score-5 anchor exactly; the score-4 anchor's 'when could be more explicit' does not apply.

5 / 5

Trigger Term Quality

Good natural keyword coverage — 'exporting RDS/Aurora data to S3', 'Athena, Glue, or Redshift Spectrum', 'backup', 'data migration' — phrases users would actually say. It is not a 5 because common variations like '.parquet', 'unload database', or 'copy database to S3' are missing; not a 3 because both service names and task-level natural phrases are present.

4 / 5

Distinctiveness Conflict Risk

A clear niche — RDS/Aurora snapshot export to S3 in Parquet for analytics services — with distinct triggers unlikely to fire for unrelated skills. It is not a 4 because the AWS-service-specific scope (RDS/Aurora, S3, Athena/Glue/Spectrum) leaves virtually no overlap risk with adjacent skills.

5 / 5

Total

19

/

20

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.

Validation — 15 / 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.