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.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 highly actionable, well-structured skill body with clear workflows and clean progressive disclosure; its main weakness is verbosity in the rubric-critical-facts section. The meta-commentary about grading could be removed without losing operational value.

Suggestions

Strip the meta-commentary about what 'the rubric grades/fails/greps for' from the 'Rubric-Critical Facts' section; state the required facts directly as operational checklists instead.

Collapse the repetitive 'you MUST tell the user ALL of the following N facts' preamble pattern into a single consistent format to reduce token overhead.

Move the per-scenario fact checklists (SSMS timeout, SSPI, Lambda/pymssql, ECS NTLM, SSM tunnel) into a reference file, keeping only the routing table inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient (command tables, constraint lists, scenario checklists), but the 'Rubric-Critical Facts to Always Surface' section is padded with meta-commentary about what 'the rubric grades' and heavy repetitive 'you MUST' framing that adds tokens without aiding execution.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: exact AWS CLI commands, the SSM document name 'AWS-StartPortForwardingSessionToRemoteHost', a complete pymssql handler catching both 18456 and pre-login timeout, and precise port/SPN/CNAME specifics.	5 / 5
Workflow Clarity	A clearly sequenced workflow (Verify Dependencies -> Classify and Route -> Execute -> verify) with explicit validation checkpoints, a confirm-before-execute gate, a refuse-and-assess list for destructive operations, and per-scenario checklists.	5 / 5
Progressive Disclosure	SKILL.md is an overview with a clear routing table pointing to 14 one-level-deep reference files, all of which exist in ./references/; content is appropriately split by driver, networking, auth, and troubleshooting topics.	5 / 5
	Total	18 / 20 Passed

Description

90%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 with excellent trigger-term coverage and clear what/when framing, narrowly limited only by generic action verbs. The trigger enumeration is comprehensive and distinctive.

Suggestions

Replace generic action phrasing ('Provides ... guidance') with concrete verbs naming what the skill does (e.g. 'Selects drivers, builds connection strings, configures SSL/Kerberos auth, and diagnoses connection failures').

Consider tightening the long trigger list into a shorter representative sample plus a catch-all clause to reduce token cost without losing discoverability.

Dimension	Reasoning	Score
Specificity	The domain is named and the 'what' is stated, but the actions ('Provides connectivity, authentication, and troubleshooting guidance') are generic verbs rather than concrete actions; the rest of the description enumerates triggers, not capabilities.	3 / 5
Completeness	Clearly states what the skill does ('connectivity, authentication, and troubleshooting guidance for Amazon RDS for SQL Server') and when to use it ('Applicable when users ask about...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural user phrasings and exact error strings ('SSMS times out connecting from EC2', 'Cannot generate SSPI context', 'auth_scheme shows NTLM instead of KERBEROS', 'error 18456') plus driver names and config tokens.	5 / 5
Distinctiveness Conflict Risk	A clearly bounded niche (RDS for SQL Server) with engine-specific error strings, driver names, and deployment patterns that make accidental triggering of unrelated skills unlikely.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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
Path: skills/specialized-skills/database-skills/rds-sqlserver/SKILL.md
Commit: 68d9e85

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.