resources

MUST use when managing resources.

Quality

45%

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/resources/SKILL.md

Quality

Content

65%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-organized, actionable reference with concrete code and a clear guardrail on the destructive deploy command, though it lacks a validation checkpoint for that command and inlines a large resource-type catalog that would benefit from a separate file.

Suggestions

Add an explicit validation/verification step for the destructive deploy, e.g., run `wmill sync diff` and confirm with the user before `wmill sync push`.

Move the nine common resource-type examples into a separate reference file and keep only one or two inline, which would improve both conciseness and progressive disclosure.

Confirm the AGENTS.wmill.md pointer resolves within the bundle, or inline the essential deploy guidance so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code blocks and short field lists with little padding of concepts Claude already knows; the only bloat is the nine fully-inlined resource-type examples. This fits 'Efficient; minor instances of over-explanation that could be trimmed' rather than 5 because the resource-type catalog is somewhat repetitive.	4 / 5
Actionability	Concrete JSON, CLI commands, and TypeScript/Python signatures are copy-paste ready and cover common cases, matching 'Mostly executable guidance; concrete code or commands with minor gaps'. It is not 5 because the script-usage examples are minimal stubs without a complete runnable call.	4 / 5
Workflow Clarity	Content is reference-style with section structure, but the destructive `wmill sync push` operation has only a cautionary guardrail and no validation/verification step; the rubric caps destructive-operation workflows at 3. It is above 2 because the deploy guardrail ('only run when the user explicitly asks') is an explicit checkpoint.	3 / 5
Progressive Disclosure	Section headers give reasonable structure, but the bulk resource-type catalog is inlined in SKILL.md rather than split out, and the only external pointer (AGENTS.wmill.md) is not part of the bundle. This fits 'Some structure but could be better organized; content that should be separate is inline' rather than 4.	3 / 5
	Total	14 / 20 Passed

Description

25%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 is a bare trigger clause with no statement of capability, giving users almost no signal about what the skill does or when specifically to invoke it. It is too vague to distinguish from other resource-related skills.

Suggestions

Add a 'what' clause naming concrete actions, e.g., 'Create, reference, and deploy Windmill resource files (.resource.json) storing credentials and config for external services.'

Expand the trigger with natural terms users actually say, such as 'Use when the user mentions Windmill resources, credentials, resource types, or $res:/$var: references.'

Tighten distinctiveness by scoping to Windmill specifically rather than the generic word 'resources'.

Dimension	Reasoning	Score
Specificity	The phrase 'managing resources' names the domain but lists no concrete actions (e.g., create, reference, deploy), matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 1 because a domain is at least named, and not a 3 because no concrete actions are enumerated.	2 / 5
Completeness	'MUST use when managing resources' gives only a vague 'when' with no 'what' describing what the skill does, matching 'only when is present without what'. A 'Use when' clause exists so it is not capped at 3 by the missing-trigger rule, but the absence of any 'what' keeps it at 2 rather than 3.	2 / 5
Trigger Term Quality	Only the single generic phrase 'managing resources' appears, with no natural synonyms or specifics users would say, fitting 'One or two generic keywords; missing the natural phrases users say'. It is above 1 because a relevant term exists, but below 3 since common variations are absent.	2 / 5
Distinctiveness Conflict Risk	'managing resources' is very broad and could overlap with many skills (compute, IAM, storage), fitting 'Very broad; high overlap risk with many similar skills'. It is not 3 because nothing narrows the niche, and not 1 because it is not totally content-free.	2 / 5
	Total	8 / 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/resources/SKILL.md
Commit: 7915540

Reviewed: 3 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.