write-script-rlang

MUST use when writing R scripts.

Quality

53%

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

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 a well-structured, actionable guide with concrete Windmill commands and runnable R examples, supported by validation checkpoints around metadata regeneration and deploy guards. Its main weakness is moderate verbosity from repeated deploy-semantics explanations.

Suggestions

Consolidate the 'not a deploy' clarification so it is stated once instead of recurring across the CLI and metadata sections.

Add one fully worked `wmill script preview` example with concrete R args to close the small actionability gap.

Consider a short numbered write→preview→generate-metadata→(deploy) sequence at the top to make the implicit workflow explicit.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and code, but the deploy-vs-not-deploy distinction is repeated across several sections and the metadata-sync prose could be tightened without losing the operational guidance.	3 / 5
Actionability	Concrete, copy-paste-ready commands (preview, generate-metadata, rehash, --dry-run, resource-type list) and complete R code examples cover the common cases, with only minor gaps like a fully worked preview-with-args invocation.	4 / 5
Workflow Clarity	Clear intent-based rules (preview vs run, deploy only when asked) plus validation checkpoints (--dry-run inspection, diffing regenerated locks, reporting version bumps before deploy), though the workflow is stated as rules rather than a numbered sequence.	4 / 5
Progressive Disclosure	A single focused file with well-organized sections (CLI Commands, R, Structure, Parameters, Resources, Output, Annotations) and clearly signaled one-level references to AGENTS.wmill.md and the preview skill; no bundle files exist to split further, which is appropriate at this size.	4 / 5
	Total	15 / 20 Passed

Description

40%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 functions purely as a trigger clause tied to a specific language niche, but it completely omits what the skill actually does, leaving the 'what' unanswered. It is distinct yet weak on capability specificity and completeness.

Suggestions

Add a concise 'what' clause naming the concrete actions, e.g. 'Write and iterate on R scripts for Windmill: define main(), manage parameters, resources, and outputs.'

Broaden trigger coverage with synonyms users might say, such as 'R code', '.R files', or 'R program'.

Keep the imperative 'MUST use when writing R scripts' but pair it with the capability sentence so both what and when are explicit.

Dimension	Reasoning	Score
Specificity	The phrase 'writing R scripts' names the domain but lists no concrete actions or capabilities at all — it tells Claude when to fire, not what the skill does.	2 / 5
Completeness	It supplies only the 'when' ('MUST use when writing R scripts') with no 'what' — the skill's purpose is never stated, matching the anchor for 'when' present without 'what'.	2 / 5
Trigger Term Quality	'writing R scripts' is a natural phrase a user would say, but it is the only trigger and omits common variations/synonyms like 'R code', '.R files', or 'R program'.	3 / 5
Distinctiveness Conflict Risk	The R-language niche is fairly distinct and unlikely to fire for unrelated skills, though the absence of any capability description leaves the trigger slightly broad.	4 / 5
	Total	11 / 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-rlang/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.