resources

MUST use when managing resources.

Quality

43%

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%

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, packed with executable JSON structures, CLI commands, and TypeScript/Python usage examples. It is well-organized but somewhat repetitive across the eight resource-type examples, monolithic with no progressive disclosure despite its length, and lacks explicit validation steps for the destructive deploy command.

Suggestions

Add a post-deploy verification step after `wmill sync push` (e.g., re-run `wmill resource list` to confirm) to create a validation checkpoint for the destructive deploy.

Condense the resource-type catalog — show the value/variable-reference pattern once, then list each type with a one-line field summary and point to `wmill resource-type get <name>` for full schemas.

Split the resource-type catalog into a separate `references/resource-types.md` linked from the overview, and surface the `AGENTS.wmill.md` deploy reference in a dedicated Deploying section rather than a buried CLI comment.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no concept-explanation fluff, but the eight resource-type examples (PostgreSQL, MySQL, Slack, S3, HTTP, Kafka, NATS, MQTT) repeat near-identical JSON patterns that could be tightened by showing the pattern once and pointing to `wmill resource-type get`.	2 / 3
Actionability	It is packed with fully executable, copy-paste-ready content: real JSON structures, concrete file-naming patterns, real CLI commands (`wmill resource list`, `wmill sync push`), and TypeScript/Python usage examples.	3 / 3
Workflow Clarity	The reference is well-organized but lacks explicit validation/verification steps for the destructive `wmill sync push` command — the caution gates when to run it rather than providing a validate-after checkpoint, so workflow clarity is capped at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	Sections are clearly headed (not a wall of text), but the ~250-line file is monolithic with a large inline resource-type catalog that could be split out, and the lone external reference (`AGENTS.wmill.md`) is buried in a CLI comment and is not present in the bundle.	2 / 3
	Total	9 / 12 Passed

Description

22%

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 provides an explicit "when" trigger but no concrete "what" — it never states the skill's actions. It uses imperative/second-person "MUST use" framing instead of third-person capability voice, and "managing resources" is generic enough to risk overlapping with unrelated skills.

Suggestions

Add a third-person capability clause stating what the skill does, e.g., "Stores credentials and configuration for external services as Windmill resources, with variable and resource references."

Add natural trigger variations users would actually say, e.g., "Use when configuring credentials, connection settings, or resource types (PostgreSQL, Slack, S3) in Windmill."

Qualify the domain with "Windmill" to reduce conflict with unrelated resource-handling skills.

Dimension	Reasoning	Score
Specificity	The phrase "managing resources" names only a domain with no concrete actions (no storing, configuring, referencing, or deploying), matching the vague "Helps with documents" anchor; it also uses imperative/second-person "MUST use" voice rather than third person, but specificity is already floored at the scale minimum.	1 / 3
Completeness	The clause "MUST use when managing resources" gives an explicit "when" trigger but states no "what" — the skill's actual capabilities are never described, and per the guideline only explicitly stated content is scored, so the missing "what" lands at the score-1 anchor.	1 / 3
Trigger Term Quality	"resources" is a natural keyword a user might say, comparable to the score-2 anchor "Works with PDF files," but coverage is thin with no common variations or specifics like credential types or service names.	2 / 3
Distinctiveness Conflict Risk	"resources" names a domain but is generic and unqualified by "Windmill," so it could overlap with unrelated resource-handling skills, fitting the score-2 "somewhat specific but could still overlap" anchor.	2 / 3
	Total	6 / 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/resources/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.