resources

MUST use when managing resources.

Quality

60%

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

76%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 strong, highly executable reference: exact file conventions, complete JSON examples, concrete CLI commands, and crisp pitfall documentation for $res/$var handling. Its main gaps are the absence of any validation/verification step around the explicitly destructive deploy command and a long inline resource-type catalog that could live in a reference file.

Suggestions

Add a validation loop around the destructive deploy, e.g. preview with "wmill resource list" / a sync diff before "wmill sync push", and verify deployed resources afterward — the current lack of validation caps workflow clarity.

Move the Common Resource Types catalog (PostgreSQL through MQTT, ~110 lines) into a references/ file (e.g. references/resource-types.md) and keep one or two exemplars inline with a clear pointer.

Trim fields Claude can infer from the remaining inline examples (standard postgres/mysql connection fields) to tighten token usage.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious workspace-specific knowledge (naming patterns, $var/$res resolution rules, wrong-vs-right wrapping examples) with almost no filler. Minor trims exist: the ~110-line Common Resource Types catalog repeats standard fields Claude could infer (e.g. postgres host/port/user), fitting anchor 4 ("efficient; minor instances of over-explanation") rather than anchor 5.	4 / 5
Actionability	Everything is copy-paste ready: exact file pattern "{path}.resource.json", complete JSON structures per resource type, runnable CLI commands ("wmill variable add '<value>' <path>"), typed TS/Python signatures, and explicit wrong-example JSON for the $res/$var wrapping pitfall. Matches anchor 5 (fully executable, covers common cases).	5 / 5
Workflow Clarity	Sequencing exists ("create or deploy the variable before the resource") and the destructive "wmill sync push" is explicitly gated to user request, but there is no validation or verification step anywhere (no preview, no post-deploy check, no error-recovery loop). The rubric caps workflow clarity at 3 for destructive operations lacking validation, which takes precedence.	3 / 5
Progressive Disclosure	No bundle files exist, so nothing is nested or mis-signaled, and sections (File Format, Secrets, Run Arguments, Common Resource Types, CLI Commands) are clearly headed and logically ordered. At ~290 lines it exceeds the under-50-line simple-skill exception, and the ~110-line resource-type catalog is reference-style content that could be split into a separate file — minor organization gaps, matching anchor 4.	4 / 5
	Total	16 / 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 six-word trigger clause with no statement of what the skill does. "Resources" is generic and unanchored to Windmill, creating both weak capability communication and high conflict risk with any other skill mentioning resources.

Suggestions

State the 'what' in third person, e.g. "Creates and deploys Windmill resource files ({path}.resource.json) for external-service credentials and configuration, and handles $res/$var references".

Add natural trigger phrases users would say: "Use when creating, editing, or deploying Windmill resources, resource types, or workspace credentials".

Include the word "Windmill" and concrete type names (postgres, slack, kafka) to distinguish this from generic 'resources' skills.

Dimension	Reasoning	Score
Specificity	The only phrases are "MUST use when managing resources" — no concrete actions are named, and the domain word "resources" is generic. It names a domain with a minimal generic action ("managing"), matching anchor 2 ("Processes PDF files"-level), not anchor 3, which requires 1-2 concrete actions.	2 / 5
Completeness	"use when managing resources" supplies only a 'when'; the 'what' is entirely missing — nothing indicates these are Windmill credential/config resource files. Exact match for anchor 2 ("only 'when' is present without 'what'"), below anchor 3 which requires a clear 'what'.	2 / 5
Trigger Term Quality	The only keywords are "resources" and "managing"; natural phrases a user would say — credentials, Windmill, resource type, postgres resource, $res — are all absent. Fits anchor 2 ("one or two generic keywords; missing the natural phrases"), below anchor 3's keyword coverage.	2 / 5
Distinctiveness Conflict Risk	"resources" is a highly generic word (cloud resources, memory resources, HR resources) with no Windmill tie-in, so it overlaps with many unrelated skills. Matches anchor 2 ("very broad; high overlap risk"), not anchor 3, which presumes at least a somewhat specific niche.	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: af42c47

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.