write-script-mssql

MUST use when writing MS SQL Server queries.

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./system_prompts/auto-generated/skills/write-script-mssql/SKILL.md

Quality

Content

72%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 content is highly actionable with executable MSSQL examples and concrete wmill command guidance, and the workflow sequencing around preview/run/deploy is clear. It loses points on conciseness (repeated caveats) and progressive disclosure (monolithic body, no bundle, soft external pointers).

Suggestions

De-duplicate the preview-vs-run-vs-deploy rules stated in both 'CLI Commands' and 'After writing' so the intent matrix appears once; this trims the redundancy holding conciseness at 3.

Add an explicit validate→fix→retry loop for `wmill script preview` failures (the body notes preview 'may cause side effects' but gives no error-handling checkpoint), which would lift workflow_clarity toward 5.

Extract the metadata-sync / dry-run / rehash procedure into a references file (e.g. references/metadata-sync.md) and link to it from a short overview section, improving progressive_disclosure from 3.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining basics Claude already knows, but the CLI-commands and metadata-sync sections restate the same preview-vs-run-vs-deploy distinctions and 'do not deploy unless asked' caveat multiple times, which could be tightened — the score-3 anchor of 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	It gives copy-paste-ready executable SQL for parameter naming, S3Object/OPENJSON consumption, and the `-- s3` streaming directive, plus concrete wmill commands with flags — fully executable guidance covering the common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	The write→preview→generate-metadata→deploy flow is clearly sequenced with explicit intent rules (preview vs run vs sync push) and a dry-run checkpoint for metadata; it stops just short of score 5 because the preview/test path has no explicit validate-on-failure→fix→retry loop, and 'preview executes and may cause side effects' is stated but not gated by a verification step.	4 / 5
Progressive Disclosure	Structure is sectioned (CLI Commands, MSSQL, S3Object, streaming) but no references/scripts/assets bundle exists and the body points to external docs only by name ('see the Deploying section in AGENTS.wmill.md', 'use the preview skill') without inline navigation signals — content that arguably belongs in a reference file (the full metadata/dry-run/rehash procedure) is inlined, fitting the score-3 anchor.	3 / 5
	Total	15 / 20 Passed

Description

33%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 appropriately narrow and distinct but severely under-specified: it states only the domain with a hard 'MUST use when' trigger and no concrete capabilities or natural trigger phrases. It reads as a routing tag rather than a capability statement.

Suggestions

Add concrete actions to the 'what', e.g. 'Write and test MS SQL Server (T-SQL) scripts in Windmill: bind @P1/@P2 parameters, consume S3Objects via OPENJSON, and stream result sets to S3'.

Add a 'Use when...' clause with natural triggers, e.g. 'Use when the user asks to write, edit, or test SQL Server / T-SQL scripts, mentions @P1 parameters or MSSQL, or needs to stream query results to S3'.

Surface the synonyms users actually say (T-SQL, SQL Server, MSSQL, stored-procedure-style scripts) so the skill matches their phrasing.

Dimension	Reasoning	Score
Specificity	The phrase 'writing MS SQL Server queries' names the domain but lists zero concrete actions — no extract/stream/parameterize/OPENJSON-style capabilities are surfaced, matching the score-2 anchor 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	Per the guideline, a missing 'Use when...' clause caps completeness at 3, and here the 'what' is also thin ('writing MS SQL Server queries') with no 'when' guidance, placing it at the score-2 anchor of a vague 'what' and no 'when'.	2 / 5
Trigger Term Quality	It surfaces only 'MS SQL Server queries' as a keyword; it lacks the natural variations and synonyms users say (T-SQL, SQL Server scripts, stored procedures, MSSQL) that would lift it to 3–4.	2 / 5
Distinctiveness Conflict Risk	MSSQL query-writing is a clear niche with distinct triggers unlikely to fire for the generic PostgreSQL/MySQL skills, so it is 'mostly distinct; minor overlap risk with closely related skills' (e.g. a sibling SQL skill).	4 / 5
	Total	10 / 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: windmill-labs/windmill
Path: system_prompts/auto-generated/skills/write-script-mssql/SKILL.md
Commit: 74af4ed

Reviewed: about 18 hours 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.