mssql

Execute read-only SQL queries against multiple Microsoft SQL Server databases. Use when: (1) querying MSSQL/SQL Server databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%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.

The body is lean, fully actionable, and well-structured around one real script reference, with no concept padding. Its one weakness is the Workflow section, which for a database skill omits an explicit validation checkpoint, capping workflow_clarity.

Suggestions

Add a validation checkpoint to the Workflow section for a database skill, e.g., step 'Verify the query is read-only and results look sane before presenting them to the user'.

Include a short feedback loop: if a query is rejected by read-only validation or times out, show the user the validation error and suggest a corrected/limited query.

Optionally note a pre-query guard such as running --schema or --tables first to confirm object names before executing a SELECT.

Dimension	Reasoning	Score
Conciseness	Lean table-driven body with no padding of concepts Claude already knows; even the 'TOP N instead of LIMIT' note earns its place by correcting a real cross-database pitfall.	5 / 5
Actionability	Copy-paste-ready commands ('python3 scripts/query.py --db production --query "SELECT TOP 10 * FROM users"'), a complete config JSON block, a config-field table, and a troubleshooting table cover the common cases fully.	5 / 5
Workflow Clarity	The Workflow section sequences four clear steps, but as a database-operations skill it lacks an explicit validation/checkpoint step (e.g., confirm read-only / verify result sanity), which the rubric's feedback-loop note caps at 3 for DB contexts.	3 / 5
Progressive Disclosure	Well-organized sections (Setup, Usage, Database Selection, Safety, Troubleshooting, Exit Codes, Workflow) with a single real, one-level-deep script reference (scripts/query.py) and no nested indirection.	5 / 5
	Total	18 / 20 Passed

Description

92%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.

The description is specific, trigger-rich, and answers both 'what' and 'when' with an explicit numbered 'Use when' clause, while staking a clear MSSQL read-only niche. Only minor trigger-term synonym coverage keeps it from a perfect sweep.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Execute read-only SQL queries', 'exploring database schemas/tables', 'running SELECT queries for data analysis', 'checking database contents') plus an explicit safety behavior ('Blocks all write operations (INSERT, UPDATE, DELETE, DROP)'), giving comprehensive coverage.	5 / 5
Completeness	Clearly answers 'what' ('Execute read-only SQL queries against multiple Microsoft SQL Server databases') and 'when' via an explicit 'Use when: (1)-(4)' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural-term coverage with synonyms ('MSSQL/SQL Server', 'schemas/tables', 'SELECT queries', 'database contents') but a few common user phrasings (e.g., 'report', 'look up', specific table mentions) are absent, stopping just short of a 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'multiple Microsoft SQL Server databases' with read-only enforcement, a clear niche with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: sanjay3290/ai-skills
Path: skills/mssql/SKILL.md
Commit: 281d88d

Reviewed: 6 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.