write-script-rust

MUST use when writing Rust scripts.

Quality

62%

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-rust/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 complete executable code and concrete commands, and the workflow is well-sequenced with explicit validation checkpoints. Its main weaknesses are repetition of the deploy-vs-test distinction and a monolithic structure that mixes generic wmill workflow with Rust-specific content.

Dimension	Reasoning	Score
Conciseness	Most content is domain-specific wmill semantics Claude would not know, but the deploy-vs-test distinction is restated across the bullet list, 'Preview vs run', and 'After writing' sections, and the metadata paragraph carries long parenthetical asides that could be tightened.	2 / 3
Actionability	It provides fully executable Rust examples (main signature, #[derive(Serialize)] return, partial cargo.toml, tokio runtime) and concrete commands with flags (e.g. 'wmill generate-metadata --dry-run', 'wmill generate-metadata rehash'), which are copy-paste ready.	3 / 3
Workflow Clarity	The workflow has explicit intent-based decision rules and real validation checkpoints — '--dry-run' to preview stale items, diffing regenerated '.lock'/'.script.lock' files, and reporting changed dependency versions — giving clear sequencing with feedback loops for the batch metadata operation.	3 / 3
Progressive Disclosure	The single SKILL.md is well-sectioned but monolithic at ~125 lines with no bundle/reference files, and the generic wmill CLI guidance (preview/run/sync/generate-metadata) is inline content that is shared across language variants and could be split into a shared reference.	2 / 3
	Total	10 / 12 Passed

Description

47%

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 has a clear, distinctive trigger, but it is written in imperative rather than third-person voice and does not describe the skill's concrete capabilities, leaving the 'what' underspecified.

Suggestions

Rewrite in third person and state capabilities, e.g. 'Writes Windmill Rust scripts with a serializable main function, partial cargo.toml dependencies, and tokio async runtime. Use when creating or editing Rust scripts for Windmill.'

Add natural trigger variations such as 'Rust script', '.rs script', or 'Windmill Rust script' so the description matches terms users actually say.

Keep the explicit 'Use when...' clause but pair it with a one-line capability list so both 'what' and 'when' are clearly answered.

Dimension	Reasoning	Score
Specificity	The description names a domain and one action ("writing Rust scripts"), which would anchor at 2, but it uses imperative/second-person voice ("MUST use") rather than third person, triggering the rubric's one-point specificity penalty, capping it at 1.	1 / 3
Completeness	An explicit 'when' trigger is present ("when writing Rust scripts"), but the 'what' is not described beyond that same phrase — the skill's concrete capabilities (main function, return types, cargo deps, async) are absent, so it does not clearly answer both.	2 / 3
Trigger Term Quality	"writing Rust scripts" is a relevant natural keyword a user might say, but it is a single phrase with no common variations (e.g. "Rust", ".rs", "cargo script"), matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The Rust language specifier carves out a clear, narrow niche ("Rust scripts") with a distinct trigger unlikely to fire for non-Rust skills, matching the 'clear niche with distinct triggers' anchor.	3 / 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-rust/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.