CtrlK
BlogDocsLog inGet started
Tessl Logo

rds-sqlserver

Provides connectivity, authentication, and troubleshooting guidance for Amazon RDS for SQL Server. Applicable when users ask about SSMS times out connecting from EC2, Cannot generate SSPI context with Windows auth, connect RDS SQL Server from Lambda with pymssql, auth_scheme shows NTLM instead of KERBEROS on ECS Fargate, SSM tunnel to RDS SQL Server from laptop, port 1433 security group, TrustServerCertificate=True for localhost tunnels, SPN MSSQLSvc, AWS Managed Microsoft AD, CNAME not RDS endpoint for Kerberos, tds_version='7.4', encryption='require', port-as-string for pymssql, Secrets Manager credential caching in Lambda, error 18456 login failed. Covers Python (pymssql, pyodbc), .NET (Microsoft.Data.SqlClient), Java (JDBC mssql-jdbc), Node.js (tedious), IAM auth via RDS Proxy, and VPC/ECS/EKS/Lambda deployment.

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

Low

Low-risk findings worth noting

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.

A highly actionable, well-structured skill body with clear workflows and a clean one-level reference routing table backed by real bundle files. Its main weakness is conciseness: meta-rubric commentary and duplicated troubleshooting content inflate the token budget without adding operational value.

Suggestions

Remove the meta-commentary about the rubric ('Each checklist below is what the rubric grades', 'the rubric explicitly greps for klist', 'the rubric fails responses that ...') — keep the operational checklists, drop the gaming narration.

Consolidate the 'Rubric-Critical Facts to Always Surface' checklists with the later Troubleshooting section to eliminate duplication, or move the long per-scenario checklists into the matching reference files.

Cut rationale clauses that restate security basics Claude already knows ('because hardcoded secrets leak into logs and source control', 'because older TLS versions have known vulnerabilities') unless they convey an RDS-SQL-Server-specific nuance.

DimensionReasoningScore

Conciseness

The body is mostly operational and actionable, but it carries notable padding: a large 'Rubric-Critical Facts to Always Surface' section with meta-commentary about what 'the rubric greps for' / 'grades as failure', repeated rationale clauses explaining basics Claude knows ('because hardcoded secrets leak into logs'), and troubleshooting content duplicated between that section and the later Troubleshooting section.

2 / 3

Actionability

Guidance is concrete and copy-paste ready: exact AWS CLI commands with flags, specific connection-string parameters (encryption='require', tds_version='7.4', port='1433'), diagnostic commands (nslookup, Test-NetConnection, klist, setspn -L), and a full executable Python handler with exception handlers.

3 / 3

Workflow Clarity

A clearly sequenced Common Tasks flow (Verify Dependencies -> Classify and Route -> Execute: driver setup, networking, auth, secrets, verify) with explicit validation checkpoints (aws --version, region enum validation, connectivity tests) and safety guardrails (mandatory user confirmation, refusal-plus-assessment for destructive ops, downtime warnings).

3 / 3

Progressive Disclosure

SKILL.md is an overview that routes to 14 one-level-deep reference files via a well-signaled scenario table, and every referenced path (references/python.md, ad-kerberos.md, rds-proxy.md, troubleshooting.md, etc.) exists in the bundle with clear navigation.

3 / 3

Total

11

/

12

Passed

Description

90%

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, trigger-rich description that clearly answers both what and when for a well-scoped niche. Its only weakness is action specificity: it leans on 'provides guidance' plus scenario triggers rather than listing distinct concrete actions.

Suggestions

Lead with concrete verbs (e.g. 'Generates connection strings, configures Kerberos/SPN and SSM tunnels, and diagnoses RDS SQL Server auth/connectivity errors') instead of the abstract 'Provides connectivity, authentication, and troubleshooting guidance'.

Trim the deepest jargon tokens (e.g. 'tds_version=7.4', 'port-as-string for pymssql') from the description; they fit better in references and slightly dilute the natural trigger terms.

DimensionReasoningScore

Specificity

The opening clause names the domain and a few actions ('Provides connectivity, authentication, and troubleshooting guidance for Amazon RDS for SQL Server'), but the concrete verbs are abstract ('provides guidance') and the bulk of the description enumerates trigger scenarios rather than distinct actions the skill performs.

2 / 3

Completeness

It explicitly states both what the skill does ('Provides connectivity, authentication, and troubleshooting guidance') and when to use it via an explicit 'Applicable when users ask about ...' trigger clause.

3 / 3

Trigger Term Quality

It covers a rich set of natural user utterances and pasted errors ('SSMS times out connecting from EC2', 'Cannot generate SSPI context', 'auth_scheme shows NTLM instead of KERBEROS', 'error 18456 login failed') that users would actually type.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply scoped to Amazon RDS for SQL Server with SQL-Server-specific triggers (SSPI, SPN MSSQLSvc, tds_version='7.4', RDS Proxy IAM auth) and explicitly names sibling skills (rds-oracle, rds-db2, amazon-aurora), making mis-routing unlikely.

3 / 3

Total

11

/

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.