alonso-skills/mssql-writing-guidelines
Use when writing or reviewing MSSQL/T-SQL, creating stored procedures, designing table schemas, writing views, building migrations, defining custom types, or architecting a SQL Server application database. Also use when writing RAISERROR patterns, CHECK constraints with scalar functions, base/subtype table hierarchies, composite key designs, role-scoped views with row-level security, or idempotent DDL scripts. If you are touching MSSQL for an application database, use this skill. Not for PostgreSQL, MySQL, Oracle, or SQLite — patterns are SQL Server-specific.
95
94%
Does it follow best practices?
Impact
98%
1.81xAverage score across 5 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that thoroughly covers specific capabilities, includes abundant natural trigger terms, explicitly states both what and when, and clearly distinguishes itself from other database skills through explicit exclusion. The description is comprehensive without being padded, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: writing/reviewing T-SQL, creating stored procedures, designing table schemas, writing views, building migrations, defining custom types, RAISERROR patterns, CHECK constraints with scalar functions, base/subtype table hierarchies, composite key designs, role-scoped views with row-level security, idempotent DDL scripts. | 3 / 3 |
Completeness | Clearly answers both 'what' (writing/reviewing T-SQL, stored procedures, schemas, views, migrations, etc.) and 'when' with multiple explicit trigger clauses: 'Use when writing or reviewing MSSQL/T-SQL...', 'Also use when...', 'If you are touching MSSQL for an application database, use this skill.' Also includes explicit exclusion criteria. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'MSSQL', 'T-SQL', 'stored procedures', 'table schemas', 'views', 'migrations', 'SQL Server', 'CHECK constraints', 'row-level security', 'DDL scripts'. Also explicitly excludes competing databases (PostgreSQL, MySQL, Oracle, SQLite) which helps with routing. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — explicitly scoped to MSSQL/SQL Server and explicitly excludes PostgreSQL, MySQL, Oracle, and SQLite. The SQL Server-specific patterns (RAISERROR, T-SQL) and the explicit exclusion clause make it very unlikely to conflict with other database skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that serves as an effective overview document for a comprehensive MSSQL methodology. It provides concrete, executable T-SQL examples throughout while maintaining clear progressive disclosure to detailed reference files. The main weakness is moderate verbosity — the Common Mistakes table largely duplicates guidance already stated in preceding sections, and a few sections could be tightened without losing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally efficient and avoids explaining basic SQL concepts, but some sections are verbose — the 'When to Use / When NOT to use' block, the Common Mistakes table (which largely restates rules already covered above), and some sections like Application Settings and Reference Tables could be tighter. However, it mostly respects Claude's intelligence and avoids padding. | 2 / 3 |
Actionability | The skill provides concrete, executable T-SQL code throughout — CREATE TYPE examples, CHECK constraint patterns, composite key hierarchies, functional constraint functions, view WHERE clauses, migration validation queries, and idempotent DDL patterns. Code is copy-paste ready and specific to SQL Server. | 3 / 3 |
Workflow Clarity | The idempotent migration section includes an explicit 4-step validation workflow with verification checkpoints (run once, verify objects, verify constraints, run again for idempotency). The transaction hierarchy (_trx/_utx/_ut) clearly defines composition patterns. The error handling section specifies explicit control flow with GOTO and @@ROWCOUNT checks after every DML. The relational queue section describes a clear claim-then-report lifecycle. | 3 / 3 |
Progressive Disclosure | The skill is an excellent overview document with well-signaled one-level-deep references to 10+ reference files (procedure-structure.md, basetype-subtype.md, hierarchical-keys.md, view-patterns.md, security-permissions.md, relational-queues.md, error-handling.md, migration-patterns.md, naming-conventions.md, etc.). Each section gives enough context to act on simple cases while pointing to detailed references for full patterns. Navigation is clear and consistent. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents