write-script-powershell

MUST use when writing PowerShell scripts.

Quality

57%

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-powershell/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 content is highly actionable with concrete commands and executable PowerShell examples, and its intent-based command selection is clear; it loses points for verbosity and for relying on an external non-bundled file plus missing an explicit deploy-validation checkpoint.

Suggestions

Add an explicit verification checkpoint before deploy (e.g. confirm `wmill generate-metadata` ran clean and the user approved the bumped dependency versions) rather than only warning not to deploy just to test.

Trim the repeated "not a deploy" restatements and consolidate the metadata-sync explanation into one concise section.

If deploy wiring details belong in AGENTS.wmill.md, summarize the essential decision (git push vs sync push) inline so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining basics Claude knows and gives operational guidance, but the metadata-sync paragraphs repeat "not a deploy" and re-explain hash propagation, so it could be tightened.	2 / 3
Actionability	Concrete commands with flags (e.g. `wmill script preview <script_path>`, `wmill generate-metadata rehash`, `wmill generate-metadata --dry-run`) and copy-paste-ready PowerShell examples with param() and typed returns are fully executable.	3 / 3
Workflow Clarity	Intent-based routing for preview vs run vs deploy is clear, but there is no explicit validate-before-proceed checkpoint for the destructive deploy step, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized and external references are signaled one level deep, but deploy detail is deferred to a non-bundled AGENTS.wmill.md and the long inline metadata section could be split.	2 / 3
	Total	9 / 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 is a crisp third-person trigger with an explicit use-when clause, but it is too terse to convey capabilities or cover natural trigger-term variations.

Suggestions

Add concrete capabilities, e.g. "Writes PowerShell scripts for Windmill: defines param() arguments, types, and return objects, and keeps generated metadata in sync."

Broaden trigger terms to include "PowerShell", ".ps1", and "PS1" alongside "PowerShell scripts".

State the "what" explicitly before the "Use when..." clause so both capability and trigger are unambiguous.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and action ("writing PowerShell scripts") but does not enumerate multiple specific actions such as structuring params, typing, or returning values, so it is not comprehensive.	2 / 3
Completeness	The explicit "when" ("MUST use when writing PowerShell scripts") is present, but the "what does this do" capability is only implied rather than stated, so it does not clearly answer both.	2 / 3
Trigger Term Quality	"PowerShell scripts" is a natural term users would say, but coverage is thin — common variations like "PowerShell", "PS1", or ".ps1" are missing.	2 / 3
Distinctiveness Conflict Risk	PowerShell is a clear niche, but the trigger could overlap with a sibling generic write-script skill when the language is unspecified, so conflict risk is not fully eliminated.	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-powershell/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.