write-script-graphql

MUST use when writing GraphQL queries.

Quality

58%

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

67%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 body is well-structured with executable commands and examples, clear decision logic, and validation checkpoints. Its main weakness is verbosity in the wmill CLI prose that assumes less of Claude's intelligence than it should.

Suggestions

Trim the wmill CLI explanatory prose into terser rules; move rationale behind each command into a short parenthetical or a reference file.

Add a brief explicit step-by-step 'after writing a script' checklist so the workflow reads as a sequence rather than scattered guidance.

Consolidate the repeated deploy-vs-preview distinctions into a single table or rule to cut duplication.

Dimension	Reasoning	Score
Conciseness	The GraphQL examples are lean, but the wmill CLI section runs to several dense paragraphs of prose that re-explain deploy-vs-local distinctions and could be tightened without losing clarity.	3 / 5
Actionability	Concrete commands (`wmill script preview`, `wmill generate-metadata`) and complete, copy-paste-ready GraphQL query/mutation examples give mostly executable guidance with only minor gaps.	4 / 5
Workflow Clarity	Decision guidance for preview vs run vs deploy is explicit, with validation checkpoints (`--dry-run`, diffing regenerated lock files) and a clear gate that deploys only on explicit request; minor gaps keep it just below 5.	4 / 5
Progressive Disclosure	Sections are well organized with headers and subheaders and no nested references; all content is inline since no bundle files exist, with external pointers (AGENTS.wmill.md, preview skill) clearly signaled.	4 / 5
	Total	15 / 20 Passed

Description

48%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 provides a clear, third-person trigger ('MUST use when writing GraphQL queries') but is too terse to fully convey capabilities, making the what and when nearly identical. Distinctiveness is decent thanks to the GraphQL focus.

Suggestions

Expand the 'what' with concrete capabilities, e.g. 'Write, structure, and parameterize GraphQL queries and mutations with variables.'

Add trigger synonyms such as 'GraphQL mutations', '.graphql files', or 'GraphQL schema' to improve trigger term coverage.

Separate the capability statement from the trigger clause so 'what' and 'when' are not circular.

Dimension	Reasoning	Score
Specificity	The phrase 'writing GraphQL queries' names the domain but offers only a single minimal, generic action; it does not list concrete capabilities like structuring queries, binding variables, or authoring mutations.	2 / 5
Completeness	It has an explicit 'when' ('MUST use when writing GraphQL queries'), but the 'what' is circular with the trigger and stays vague about what the skill actually does, so it does not reach a clear dual answer.	3 / 5
Trigger Term Quality	'writing GraphQL queries' is a natural phrase users say, but it misses common variations/synonyms such as mutations, .graphql files, or schema introspection.	3 / 5
Distinctiveness Conflict Risk	'GraphQL queries' carves a clear niche with low conflict risk, though the minimal wording leaves minor overlap with general coding/SDK skills.	4 / 5
	Total	12 / 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-graphql/SKILL.md
Commit: 74af4ed

Reviewed: about 19 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.