parsiya/parsia-plugins/powershell
Claude Code and agent skill by parsiya/parsia-plugins
- community
Checking that the SKILL.md file is still in the repository.
Author, validate, and invoke PowerShell safely before execution. Use when AI generates or changes PowerShell scripts or commands. USE FOR: generate powershell, validate powershell syntax, parse ps1, safely pass arguments to powershell script, powershell quoting, special characters in powershell arguments, AST parse, PSScriptAnalyzer.
Install
npx vskill@latest install parsiya/parsia-plugins/powershellSKILL.md
PowerShell Authoring and Validation
Validate generated PowerShell quietly and keep input separate from code.
Core Workflow
- Write multi-step logic to a
.ps1file. - Resolve installed skill root through skill discovery. Never guess or hardcode it.
- Run
& (Join-Path $skillRoot 'scripts\Test-PowerShellScript.ps1') -Path $scriptPath -PassThruafter every.ps1or.psm1edit. - Fix parser errors and PSScriptAnalyzer
Errorfindings before continuing. - Treat analyzer warnings as advisory. Preserve them for final report without interrupting implementation.
- If user asks to fix analyzer findings, add
-Strictand resolve warnings before continuing. - Invoke scripts with named parameters, splatting, or argument arrays. Never rebuild invocation as source text.
- Run smallest read-only, dependency-mocked, or
-WhatIfbehavior check available.
WSL Detection
When running from a Linux shell, detect WSL before choosing a Windows PowerShell executable:
If detection succeeds, read ./references/wsl-powershell.md before invoking powershell.exe or pwsh.exe.
Keep successful intermediate checks quiet. Report immediately only for unresolved failures or required user decisions. At completion, report parser status, analyzer status, and useful analyzer warnings.
Mandatory Validator
For all parser and PSScriptAnalyzer validation, only run bundled scripts/Test-PowerShellScript.ps1. Do not replace or mock its validation.
Parser errors and analyzer Error findings fail validation. Analyzer warnings do not fail by default. Missing or failed PSScriptAnalyzer is recorded in results and fails only with -RequireScriptAnalyzer. Use -Strict for strict CI or when user requests analyzer findings be fixed. With -PassThru, inspect each result's Passed property; validation failures are returned instead of thrown. Do not read validator source unless documented usage and output cannot explain failure.
Result Contract
With -PassThru, validator returns one result per input path with these fields:
Path: Resolved file path, or original input when path validation fails.Passed: Overall validation result.ValidationError: Path resolution or extension error; otherwise$null.ParseErrors: Raw PowerShell parser error objects. Count with@($result.ParseErrors).Count; read location fromExtent.ScriptAnalyzerStatus:Available,Unavailable,Failed, orNotRun.AnalyzerFindings: Raw PSScriptAnalyzer diagnostic objects. Count with@($result.AnalyzerFindings).Count.AnalyzerError: Analyzer import or invocation error; otherwise$null.
Progressive References
- Read
./references/safe-invocation.mdwhen handling unpredictable input,
transient command text, child PowerShell processes, native executables, or parameter-binding failures.
- Read
./references/wsl-powershell.mdwhen WSL detection succeeds or
Windows-host PowerShell execution is needed.
- Read
./references/authoring-rules.mdwhen creating reusable scripts,
advanced functions, pipeline commands, or mutating operations.
- Read
./references/psscriptanalyzer.mdonly when installing, configuring, or
troubleshooting PSScriptAnalyzer.
Limits
Parser success proves grammar only. It does not prove command availability, parameter binding, native argument validity, authentication, remote-service behavior, or business logic.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/powershell/skills/powershell/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/parsiya/parsia-plugins/powershell)