CtrlK
BlogDocsLog inGet started
Tessl Logo

rds-db2

Provisions, connects, migrates, and operates Amazon RDS for Db2. Applies when provisioning with IBM customer and site IDs (License Manager, BYOL, GovCloud), connecting over TLS, fixing SQL30082N after Secrets Manager rotation, migration from Db2 LUW (Linux, AIX, Windows, AS400) or z/OS mainframe (ADB2GEN, Q Replication), choosing code page/collation (EBCDIC, CCSID), S3 backup/restore, Multi-AZ and cross-region standby replicas, RDSADMIN procedures, customer-managed KMS BYOK, self-managed Active Directory Kerberos, Db2 audit to S3, minimum IAM, or colocation.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 strong, highly actionable skill body with precise commands, signatures, and error-recovery loops, well-structured around a routing table to a rich bundle. Its main weakness is length: a large inline 'must-surface facts' block and some cross-section constraint repetition dilute conciseness and keep progressive disclosure from a top score.

Suggestions

Move the eight numbered 'RDS-managed facts the agent must always surface' lists into a dedicated reference (e.g. references/rds-managed-facts.md) and keep only a short pointer plus the one or two highest-frequency facts inline, to improve both conciseness and progressive disclosure.

Consolidate the repeated credential-handling constraint ('MUST NOT prompt the user to paste credentials') into a single stated rule in Verify Dependencies and reference it from Execute Workflow and Security Considerations instead of restating it verbatim.

Tighten the Execute Workflow phase into an explicit numbered sequence with validation checkpoints (collect params → validate formats → run command → poll task status) so the workflow matches the precision of the routing and troubleshooting sections.

DimensionReasoningScore

Conciseness

Content is high-signal and RDS-Db2-specific rather than padded with concepts Claude knows, but the ~80-line inline 'RDS-managed facts the agent must always surface' block and repeated credential-handling constraints across sections add length that could be tightened or offloaded to references.

3 / 5

Actionability

Fully executable guidance throughout: exact AWS CLI commands ('aws rds create-db-instance-read-replica --replica-mode mounted …'), precise rdsadmin signatures ('rdsadmin.restore_database(dbname, type, prefix, bucket, region)'), concrete tag syntax, and an error→cause→fix troubleshooting table.

5 / 5

Workflow Clarity

Clear three-phase sequence (Verify Dependencies → Classify and Route → Execute Workflow) with an explicit dependency-validation gate and troubleshooting feedback loops; the Execute Workflow phase reads as guidance rather than a crisp numbered sequence with checkpoints, keeping it just below the top anchor.

4 / 5

Progressive Disclosure

Excellent routing table maps user phrases to 15 real one-level-deep references plus 8 scripts and assets (all verified to exist), but the large inline mandatory-facts section is detailed content that arguably belongs in a reference, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

100%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.

An exemplary description: concrete actions, comprehensive natural trigger terms, explicit what-and-when guidance, and a narrow niche with minimal conflict risk. No verbosity penalty despite its length because every clause names a distinct, scoping capability.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Provisions, connects, migrates, and operates Amazon RDS for Db2') with comprehensive coverage across the full operator lifecycle; no vague or abstract language.

5 / 5

Completeness

Explicitly answers both 'what' (provisions/connects/migrates/operates RDS for Db2) and 'when' via the 'Applies when … or colocation' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and error codes a user would actually say: 'SQL30082N', 'License Manager', 'BYOL', 'GovCloud', 'ADB2GEN', 'Q Replication', 'EBCDIC', 'CCSID', 'Multi-AZ', 'Kerberos'.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to Amazon RDS for Db2 with highly specific triggers (ADB2GEN, RDSADMIN, mounted standby replicas) that would not fire for any other database skill.

5 / 5

Total

20

/

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.

Validation15 / 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.