write-script-powershell

MUST use when writing PowerShell scripts.

Quality

61%

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

82%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 content is highly actionable with concrete wmill commands and executable PowerShell examples, organized into a clear sequenced workflow with sensible validation checkpoints. It is slightly verbose in the metadata-sync section and could benefit from splitting longer reference material into bundled files.

Suggestions

Tighten the "Keep metadata in sync" paragraph by moving the auto-vs-manual defaults rationale into a shorter conditional rule.

Add an explicit validate-fix-retry loop for the deploy step, e.g. preview → if errors, fix and re-preview → only then sync push.

Consider extracting the wmill CLI command reference into a references/ file so the SKILL.md body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence about wmill-specific workflow rules and PowerShell basics, with only minor over-explanation in the metadata-sync section. It fits the score-4 anchor of efficient content with minor trims possible; it is not score 5 because a few passages (e.g. the generate-metadata defaults rationale) could be tightened.	4 / 5
Actionability	The skill provides concrete executable commands (`wmill script preview <script_path>`, `wmill generate-metadata --dry-run`, `wmill generate-metadata rehash`) and copy-paste-ready PowerShell code blocks covering structure, parameter types, and return values. This matches the score-5 anchor of fully executable, copy-paste-ready guidance covering the common cases.	5 / 5
Workflow Clarity	There is a clear sequenced workflow (write → preview by intent → generate-metadata to sync → deploy only when asked) with validation checkpoints such as preview-before-deploy, `--dry-run`, and diffing dependency versions. It fits the score-4 anchor of a clear sequence with most checkpoints present; it is not score 5 because there is no explicit validate-fix-retry feedback loop or checklist.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized with clear section headers and a signaled one-level external reference ("see the Deploying section in AGENTS.wmill.md"), and no nested or buried references. It fits the score-4 anchor of good structure with minor gaps; it is not score 5 because the ~105-line body is not split into reference files and the simple-skill under-50-lines exception does not apply.	4 / 5
	Total	17 / 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 is a clear trigger clause but omits any capability statement, so it answers "when" but not "what." It is distinct and uses a natural keyword yet is too terse to be comprehensive.

Suggestions

Add a concrete "what" clause naming the skill's capabilities, e.g. "Writes, previews, and syncs PowerShell scripts for wmill."

Broaden trigger coverage with synonyms and file extensions such as ".ps1", "cmdlet", or "PowerShell scripting".

Combine what and when into one sentence, e.g. "Write and preview PowerShell scripts for wmill. Use when creating or editing .ps1 scripts."

Dimension	Reasoning	Score
Specificity	The phrase "writing PowerShell scripts" names the domain but lists no concrete capabilities (no writing, editing, previewing, or metadata actions), matching the score-2 anchor of naming a domain with minimal actions. It is above score 1 because it is not pure abstract language, but below score 3 because no 1-2 concrete actions are described.	2 / 5
Completeness	The description only states when to use the skill ("MUST use when writing PowerShell scripts") with no statement of what it does, matching the score-2 anchor where only "when" is present without "what". It is not score 3 because there is no clear "what" at all.	2 / 5
Trigger Term Quality	"PowerShell" and "writing PowerShell scripts" are natural terms a user would say, but coverage is thin with no variations or synonyms (.ps1, cmdlet, scripting). This matches the score-3 anchor of some relevant keywords missing common variations; it is not score 4 because keyword coverage is not broad.	3 / 5
Distinctiveness Conflict Risk	The PowerShell-specific trigger carves a clear niche with minimal conflict risk, though it may overlap with sibling write-script skills for other languages. This fits the score-4 anchor of mostly distinct with minor overlap risk; it is not score 5 because the description lacks the richness and explicit trigger phrases of the score-5 example.	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-powershell/SKILL.md
Commit: 74af4ed

Reviewed: about 18 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.