write-script-graphql

MUST use when writing GraphQL queries.

Quality

46%

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-graphql/SKILL.md

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is actionable and well-organized for a simple skill, with concrete wmill commands and clean GraphQL examples. Its main weakness is repetition in the CLI section and only implicit verification checkpoints for the query-writing workflow.

Suggestions

Consolidate the repeated 'not a deploy / pushing is a deploy' reminders into a single concise callout to tighten conciseness toward a 3.

Add one executable end-to-end example binding a GraphQL query to a wmill script invocation with sample args, so the GraphQL guidance becomes copy-paste ready.

Make the query-testing step an explicit validation checkpoint (e.g. 'after writing the query, run `wmill script preview <path> -d '<args>'` and confirm the result') to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The CLI section is dense and accurate but repeats the 'generate-metadata is not a deploy / pushing is a deploy' point across multiple paragraphs and re-explains intent distinctions redundantly, so it is mostly efficient but could be tightened toward a 3.	2 / 3
Actionability	Concrete commands like `wmill script preview <script_path>` and `wmill generate-metadata --dry-run` are present and useful, but the GraphQL section's examples use placeholders (`<script_path>`, no binding invocation) and never show the executable wmill script wrapper, leaving key details incomplete versus copy-paste-ready.	2 / 3
Workflow Clarity	The preview-vs-run and metadata-sync flows are sequenced with clear decision rules, but the verification step for the GraphQL query itself (e.g. previewing a query with sample args) is implicit rather than an explicit checkpoint, so checkpoints are present but not fully explicit per the 3-anchor.	2 / 3
Progressive Disclosure	With no bundle files present and the body under ~95 lines, the skill is a single self-contained overview split into clearly headed, well-organized sections (CLI Commands, GraphQL, Structure, Variables, Mutations) with no nested references, which per the rubric's simple-skill note earns a 3.	3 / 3
	Total	9 / 12 Passed

Description

35%

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 explicit but too thin: it states only one action and reuses it as the trigger, offering no natural keyword variations or situational cues. It would benefit from naming mutations/variables and richer user-facing trigger terms.

Suggestions

Enumerate concrete actions beyond just queries, e.g. 'Write GraphQL queries and mutations, bind variables as script arguments.' to lift specificity to a 3.

Expand the trigger to natural phrases users actually say, e.g. 'Use when the user asks to write, edit, or test a GraphQL query or mutation against a GraphQL API.'

Add a situational when-clause distinct from the what-clause so it clearly answers both 'what' and 'when' and reduces overlap with generic coding skills.

Dimension	Reasoning	Score
Specificity	The phrase 'writing GraphQL queries' names the domain and one concrete action but enumerates no other capabilities (mutations, variables, schema), matching the 'names domain and some actions' anchor rather than the multiple-specific-actions anchor.	2 / 3
Completeness	It states what the skill does ('writing GraphQL queries') and includes an explicit 'Use when...' trigger ('MUST use when writing GraphQL queries'), but the when-clause is a near-tautology of the what-clause with no situational triggers, so it does not clearly answer both as required for a 3.	2 / 3
Trigger Term Quality	The only natural user-facing keyword is 'GraphQL queries'; there are no common variations users would say ('queries', 'mutations', 'API', 'GraphQL API'), so it sits closer to the minimal-keyword anchor than to 'some relevant keywords'.	1 / 3
Distinctiveness Conflict Risk	The GraphQL niche is fairly distinct, yet the generic phrasing could overlap with general coding/API skills and offers no discriminating triggers beyond the skill name, fitting the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	7 / 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-graphql/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.