write-script-mssql

MUST use when writing MS SQL Server queries.

Quality

57%

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

65%

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 concrete commands and executable SQL examples, and it is well-sectioned, but it is a monolithic, somewhat repetitive file whose multi-step workflow guidance is scattered through prose rather than presented as an explicit sequenced checklist with validation checkpoints.

Suggestions

Consolidate the repeated "deploy only when the user explicitly asks" guidance into one stated-once rule to remove duplication across the CLI list, preview-vs-run, and after-writing sections.

Render the write -> preview -> generate-metadata -> deploy flow as a short numbered checklist with explicit validation checkpoints (e.g. run --dry-run, diff .lock, confirm with user) instead of prose conditionals.

Move the general Windmill CLI/metadata-sync material into a bundled reference file (e.g. references/wmill-cli.md) and keep SKILL.md as a concise MSSQL-focused overview that links to it, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no basic concept explanations), but repeats the "deploy only when explicitly asked" guidance across the CLI list, preview-vs-run, and after-writing sections, and the metadata-sync passage is long and could be tightened. Mostly efficient but not lean enough for 3.	2 / 3
Actionability	It provides fully executable commands (wmill script preview/run, generate-metadata, generate-metadata rehash, resource-type list --schema) and complete, copy-paste-ready SQL examples for @P1/@P2 parameters, OPENJSON S3Object consumption, and the -- s3 streaming directive. This matches the score-3 anchor of concrete, executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	Intent sequencing (write -> preview -> generate-metadata -> deploy only when asked) and validation cues (dry-run, diffing .lock files, preview before deploy) are present, but they are scattered through prose and conditionals rather than a crisp numbered sequence with explicit checkpoints. Validation exists (above 1) but is not a clean sequenced checklist (below 3).	2 / 3
Progressive Disclosure	The body is well-sectioned with clear headers (not a wall of text, no nested references, so above 1), but it is a single monolithic file over 50 lines mixing general Windmill CLI guidance with MSSQL-specific material, with no bundle reference files to split content into. Structured but not appropriately split (below 3).	2 / 3
	Total	9 / 12 Passed

Description

50%

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 accurate and explicitly triggered but very terse — a single clause that conflates the "what" and the "when" without naming the skill's real capabilities or common trigger variations. It lands at the midpoint across all dimensions.

Suggestions

Separate the what from the when, e.g. "Write, preview, and sync MS SQL Server (MSSQL) scripts in Windmill. Use when writing or testing MSSQL queries, stored procedures, or @P-parameterized scripts."

Add common trigger variations users would actually say (MSSQL, T-SQL, stored procedures, SQL Server scripts) to improve trigger-term coverage and reduce overlap with sibling write-script skills.

Mention the Windmill context so the skill is distinguishable from generic SQL helpers.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain and a single action ("writing MS SQL Server queries"), but does not list multiple specific actions like the score-3 anchor (e.g. write, preview, sync metadata, stream to S3). It is concrete rather than vague, so it is above 1, but not comprehensive enough for 3.	2 / 3
Completeness	An explicit "MUST use when" trigger answers the "when", and "writing MS SQL Server queries" supplies a "what", but the what merely restates the trigger rather than articulating the skill's actual capabilities. Both elements are present (above 1), but the what is not clearly or distinctly stated (below 3).	2 / 3
Trigger Term Quality	"MS SQL Server queries" and "writing" are natural terms a user might say, but coverage is narrow and omits common variations such as MSSQL, T-SQL, stored procedures, or scripts. Relevant keywords are present but incomplete, matching the score-2 anchor rather than the broad coverage expected at 3.	2 / 3
Distinctiveness Conflict Risk	"MS SQL Server" is a specific niche, but the description omits the windmill/script framing, leaving overlap risk with sibling write-script skills, and "writing queries" narrows the trigger below the skill's full scope. It is more specific than the generic score-1 examples but not a clear, conflict-free niche.	2 / 3
	Total	8 / 12 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: 33d2845

Reviewed: 2 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.