CtrlK
BlogDocsLog inGet started
Tessl Logo

rds-oracle

Diagnoses and resolves Amazon RDS for Oracle connectivity, authentication, networking, and driver troubleshooting. Applicable to any RDS-for-Oracle question including connecting a Python Lambda to RDS Oracle in a VPC with pooling and cold-start optimization, EKS pods to RDS Oracle via the Secrets Manager CSI driver with IRSA and SecretProviderClass, ORA-12170 cross-VPC timeouts from EC2, DPI-1047 cannot-locate-64-bit-Oracle-Client errors, and Oracle Connection Manager (CMAN) on EC2 as a proxy with HA across two AZs. Covers python-oracledb thin vs thick mode, init_oracle_client, RDS Proxy does NOT support RDS Oracle, port 1521, VPC peering, Transit Gateway, Kerberos with AWS Managed Microsoft AD, SSL/TLS/NNE, SSM port forwarding, EC2/ECS Fargate/EKS/Lambda, SQL Developer/DBeaver/Toad/SQLcl, and Secrets Manager.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is exceptionally actionable with concrete AWS CLI commands, exact ORA-error fixes, and a well-sequenced workflow with validation checkpoints, and its progressive disclosure is exemplary — a concise overview routing to eight real one-level-deep references. Its main weakness is conciseness: it contains grader-oriented meta-comments and repeats key facts across sections.

Suggestions

Remove meta-references to a rubric/grader — e.g. 'the rubric greps for these', 'the rubric catches', and the section title 'Rubric-Critical Facts to Always Surface' — these pad the skill and signal the content is written to satisfy a grader rather than to guide the user.

Consolidate the 'RDS Proxy does NOT support RDS Oracle' fact, which is stated in the Overview, Security Considerations, Execute Workflow constraints, and again in the CMAN section, into one canonical statement referenced where needed.

Move the per-scenario 'MUST tell the user ALL of the following' checklists (Lambda, EKS, ORA-12170, DPI-1047, CMAN) into their corresponding sub-skill references rather than keeping them inline, since they duplicate guidance already implied by the routing table.

DimensionReasoningScore

Conciseness

Mostly efficient and dense with useful specifics, but includes unnecessary padding: meta-references to a grader ('the rubric greps for these', 'the rubric catches', a section titled 'Rubric-Critical Facts to Always Surface') and repetition of the 'RDS Proxy does NOT support RDS Oracle' fact across the Overview, Constraints, and CMAN sections. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the lean level-3 anchor.

2 / 3

Actionability

Provides concrete, executable guidance throughout — real AWS CLI commands ('aws ec2 authorize-security-group-ingress --group-id sg-123 --protocol tcp --port 1521 --source-group sg-456'), specific YAML structures (SecretProviderClass, IRSA via eksctl), exact ORA-error fixes, and bundled diagnostic scripts — copy-paste ready, matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

Clear sequence (Verify Dependencies → Classify and Route → Execute Workflow) with explicit validation checkpoints: dependency verification before code generation, a routing table mapping symptoms to references, and diagnostic feedback loops in the troubleshooting table ('run test_connectivity.sh; if TCP fails, check SG inbound + route tables'). Destructive operations are refused with an offered assessment workflow, satisfying the feedback-loop requirement.

3 / 3

Progressive Disclosure

Clear overview routing to eight one-level-deep sub-skill references (networking.md, connection-auth.md, etc.) plus four language references and five bundled scripts — all verified to exist as real files, each referenced with a clear markdown link in a routing table, matching the 'clear overview with well-signaled one-level-deep references' anchor.

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.

The description is highly specific, written in third person, and rich with natural trigger terms users would actually say. It explicitly answers both what the skill does and when to use it, and occupies a distinct niche unlikely to conflict with sibling skills. Its only weakness is verbosity — it is dense but long, though nearly every clause earns its place as a trigger term rather than fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Diagnoses and resolves ... connectivity, authentication, networking, and driver troubleshooting') and enumerates specific scenarios (Python Lambda to RDS Oracle, EKS via CSI driver with IRSA, ORA-12170, DPI-1047, CMAN on EC2), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Answers both 'what' ('Diagnoses and resolves...') and 'when' via an explicit 'Applicable to any RDS-for-Oracle question including...' trigger clause, satisfying the 'clearly answers both what AND when with explicit triggers' anchor; not capped at 2 because a trigger clause is present.

3 / 3

Trigger Term Quality

Strong coverage of natural terms users would say: ORA-12170, DPI-1047, python-oracledb, EKS, Secrets Manager, Connection Manager/CMAN, port 1521, VPC peering, Transit Gateway, Kerberos, SQL Developer/DBeaver/Toad/SQLcl — matching the 'good coverage of natural terms' anchor rather than the 'some relevant keywords but missing variations' level below.

3 / 3

Distinctiveness Conflict Risk

A clear niche (Amazon RDS for Oracle connectivity) with distinctive triggers (ORA error codes, CMAN, 'RDS Proxy does NOT support RDS Oracle') unlikely to fire for other skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

12

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.