write-script-mysql

MUST use when writing MySQL queries.

Quality

63%

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-mysql/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 body is highly actionable with concrete commands, executable SQL examples, and a well-sequenced workflow carrying real validation checkpoints, but it is verbose in places and keeps everything inline rather than splitting generic Windmill guidance from MySQL-specific material.

Suggestions

Tighten the generate-metadata prose by moving extended rationale (version-bump behavior, strict-folder-boundaries, import propagation) into a terse rule list or a reference file.

Consider splitting the generic Windmill CLI/metadata guidance into a shared reference so SKILL.md leads with the MySQL-specific overview and links out for the dev-loop detail.

Trim repeated 'not a deploy' reminders to a single stated rule to recover token budget.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational Windmill guidance Claude would not already know, but the generate-metadata section is padded with lengthy rationale (version bumps, strict-folder-boundaries, import propagation) that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	It provides specific, copy-paste-ready commands (wmill script preview/run, generate-metadata --dry-run, generate-metadata rehash) and complete executable SQL examples (? placeholders, JSON_TABLE binding, -- s3 directive), matching 'fully executable code/commands; specific examples'.	3 / 3
Workflow Clarity	The write -> preview-vs-run -> generate-metadata -> deploy flow is sequenced with explicit decision rules and validation checkpoints (dry-run to list stale items, diffing lock files to catch version bumps, rehash vs full regenerate), matching 'clear sequence with explicit validation steps'.	3 / 3
Progressive Disclosure	Sections are well-organized and references are only one level deep (AGENTS.wmall.md, the preview skill), but no bundle files exist and all ~90 lines live inline in SKILL.md, so content that could be split (the generic CLI/metadata guidance vs MySQL specifics) is not, fitting 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 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 terse and carries an explicit use-when trigger with a clear MySQL niche, but it states only a single action and does not elaborate on what the skill actually does, leaving it flat across all dimensions.

Suggestions

Add 1-2 concrete capability phrases, e.g. 'Write MySQL scripts with ? placeholders, bind S3Object parameters, and stream results to S3', to lift specificity and completeness.

Include natural trigger variations users say, such as 'MySQL queries', 'SQL scripts', or 'MySQL statements', to improve trigger-term coverage.

Briefly separate the 'what' from the 'when' so the skill's capabilities are distinct from its trigger condition.

Dimension	Reasoning	Score
Specificity	It names a clear domain and a single action ("writing MySQL queries") but does not enumerate multiple concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It has an explicit 'when' trigger ("MUST use when...") but the 'what' is thin and indistinguishable from the trigger, so it does not clearly answer both; this sits at 'has what, but when is only weakly paired' rather than the fuller level-3 example.	2 / 3
Trigger Term Quality	"writing MySQL queries" is a natural phrase a user might say, but it offers only one variation and omits common forms like "SQL query" or "MySQL script", fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	"MySQL queries" carves a specific niche, but the body references sibling SQL dialects (PostgreSQL, Snowflake, MSSQL, BigQuery), so it could overlap with sibling write-script skills, matching 'somewhat specific but could still overlap with similar skills'.	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-mysql/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.