write-script-rlang

MUST use when writing R scripts.

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-rlang/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 executable commands and code, and the workflow is clearly sequenced with explicit verification checkpoints. It is somewhat verbose in the CLI/metadata sections and keeps all guidance inline rather than progressively disclosing the generic wmill workflow into a separate reference.

Suggestions

Consolidate the 'only deploy when explicitly asked' caution, which is stated in at least three places, into a single authoritative statement to reduce repetition.

Consider moving the generic wmill CLI workflow guidance (preview vs run, sync push, metadata sync) into a shared reference file and keeping SKILL.md focused on R-specifics with a brief pointer.

Trim the 'Keep metadata in sync' paragraph by separating the rationale from the imperative steps so the required action is scannable.

Dimension	Reasoning	Score
Conciseness	The R sections are lean with executable examples, but the CLI/metadata guidance repeats the deploy-only-when-asked caution several times and the 'Keep metadata in sync' paragraph is wordy; it is mostly efficient but could be tightened.	2 / 3
Actionability	Concrete wmill commands with arguments (e.g. 'wmill script preview <script_path>', 'wmill generate-metadata --dry-run', 'wmill generate-metadata rehash') and complete, copy-paste-ready R code examples for main, parameters, resources, and output are provided throughout.	3 / 3
Workflow Clarity	A clear write -> preview-by-intent -> sync-metadata -> offer-test -> deploy-when-asked sequence is given, with explicit checkpoints such as 'diff the regenerated .lock/.script.lock files and tell the user which dependency versions changed' and a '--dry-run ... then narrow with a path argument' feedback loop for the batch metadata operation.	3 / 3
Progressive Disclosure	Sections are well-organized and external references (AGENTS.wmill.md, the preview skill) are clearly signaled and one level deep, but the substantial generic wmill CLI workflow guidance is inline in a single ~135-line SKILL.md rather than split into a shared reference, so content that could 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 has a strong explicit trigger and names the R-script domain, but it is extremely terse and conflates the 'what' with the 'when' without listing concrete capabilities or natural trigger variations. It is adequate but thin across all dimensions.

Suggestions

List concrete capabilities, e.g. 'Define a main function, map R types to Windmill types, use resources and variables, and run via wmill script preview.'

Add natural trigger variations such as 'R scripts, R code, .R files, or statistics scripts.'

Separate the 'what' (capabilities) from the 'when' (trigger) so the description clearly answers both, e.g. '... Use when the user asks to write or edit R scripts for Windmill.'

Dimension	Reasoning	Score
Specificity	It names a domain ('R scripts') and one action ('writing'), which is above the vague anchor, but it does not list multiple concrete capabilities like the score-3 example does.	2 / 3
Completeness	An explicit trigger is present ('MUST use when writing R scripts'), so it is not capped at 2 by the missing-trigger rule, but the 'what' is minimal and conflated with the 'when' rather than clearly listing distinct capabilities.	2 / 3
Trigger Term Quality	'writing R scripts' and 'R scripts' are natural terms a user would say, but common variations such as 'R code', '.R files', or 'statistics script' are missing.	2 / 3
Distinctiveness Conflict Risk	'R scripts' is a fairly clear niche, but the terse 'MUST use when writing R scripts' pattern likely overlaps with sibling language skills and relies on a single word to distinguish them.	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-rlang/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.