write-script-snowflake

MUST use when writing Snowflake queries.

Quality

50%

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-snowflake/SKILL.md

Quality

Content

77%

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 commands and complete Snowflake SQL examples, and its workflows are clearly gated with dry-run inspection and deploy-only-on-ask checkpoints. Its main weakness is conciseness and structure: the metadata-sync caveats are wordy and the single-file layout could externalize detail.

Suggestions

Tighten the metadata-sync section: collapse the dependency-bump and import-propagation caveats into a short bullet list to cut token overhead.

Move the detailed generate-metadata rehash/dry-run mechanics into a bundled reference file, keeping SKILL.md as a concise overview with a one-level-deep link.

Consider a brief inline validation step after editing Snowflake scripts (e.g. preview before offering to deploy) to make the existing deploy gate even more explicit.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and free of concept-padding, but the metadata-sync section runs into long caveat paragraphs about dependency bumps and lock propagation that could be tightened, fitting the score-2 anchor of mostly efficient with some unnecessary explanation.	2 / 3
Actionability	It provides fully executable commands (wmill script preview, generate-metadata --dry-run) and copy-paste-ready Snowflake SQL with exact ? placeholder syntax and PARSE_JSON/LATERAL FLATTEN examples, matching the score-3 anchor for concrete copy-paste-ready guidance.	3 / 3
Workflow Clarity	Multi-step decisions are clearly sequenced with explicit gates ("Only use script run when...", deploy only on explicit ask) and a feedback loop (run generate-metadata, diff the .lock, report changed versions, --dry-run to inspect before acting), matching the score-3 anchor of clear sequence with validation checkpoints.	3 / 3
Progressive Disclosure	It is a single well-sectioned file with no nested references, but at ~90 lines it is monolithic and references external docs (AGENTS.wmill.md, AGENTS.md, the preview skill) by name rather than splitting detailed metadata caveats into a bundled file, fitting the score-2 anchor of content that should be separate being inline.	2 / 3
	Total	10 / 12 Passed

Description

22%

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 short and provides a clear trigger ("MUST use when writing Snowflake queries") but fails to state what the skill actually does, leaving its capabilities unspecified. It is distinct enough for Snowflake work yet too vague on actions and trigger-term coverage.

Suggestions

Add concrete capabilities, e.g. "Write Snowflake SQL scripts in Windmill: declare ?-parameterized queries, parse S3 objects, and stream result sets to S3."

Expand trigger terms to include natural variations like "Snowflake SQL", "Snowflake script", or "Windmill Snowflake query" for better recall.

Combine what + when into one sentence, e.g. "Write and preview Snowflake SQL scripts in Windmill. Use when the user asks to write, edit, or test a Snowflake query."

Dimension	Reasoning	Score
Specificity	The description "MUST use when writing Snowflake queries" names the domain (Snowflake queries) but states no concrete actions or capabilities, matching the score-1 anchor of vague/abstract language with no enumerated actions.	1 / 3
Completeness	It provides a "when" trigger but omits any "what does this skill do" — the reader cannot tell whether it writes, optimizes, or converts Snowflake queries — so the score-1 anchor of missing what OR when applies.	1 / 3
Trigger Term Quality	"Snowflake queries" is a natural term a user would say, but coverage is thin with no common variations or synonyms, fitting the score-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	The Snowflake-specific framing gives it a recognizable niche unlikely to collide with unrelated skills, but the generic "queries" phrasing leaves some overlap risk with other SQL/data skills, matching the score-2 anchor.	2 / 3
	Total	6 / 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-snowflake/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.