Skip to content

JordanGunn/nunchuck / skills/md/md-review

md-review

Verified

Agent review for markdown quality, clarity, and structural integrity. Leverages deterministic lint output as input for subjective assessment.

scripts/skill.ps1

View on GitHub
$ErrorActionPreference = "Stop"

$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
$IncludeDir = Join-Path $ScriptDir "include"

$ConfigPath = Join-Path $ScriptDir ".config.ps1"
if (Test-Path $ConfigPath) {
    . $ConfigPath
}

function Show-Help {
    @"
md-review - Agent review for markdown quality and structure

Commands:
  help
  validate

Usage:
  md-review <file|dir>
  md-review help
  md-review validate

Deterministic behavior:
- Runs deterministic lint checks on the target (read-only)
- Prints lint findings for use by the agent during review
"@
}

function Invoke-Validate {
    $errors = 0

    if (-not (Get-Command uv -ErrorAction SilentlyContinue)) {
        Write-Error "error: uv not found. Install from https://docs.astral.sh/uv/"
        $errors++
    }

    $pyproject = Join-Path $IncludeDir "pyproject.toml"
    if (-not (Test-Path $pyproject)) {
        Write-Error "error: missing $pyproject"
        $errors++
    }

    $cli = Join-Path $IncludeDir "md_review_cli.py"
    if (-not (Test-Path $cli)) {
        Write-Error "error: missing $cli"
        $errors++
    }

    if ($errors -gt 0) {
        exit 1
    }

    Write-Output "ok: md-review skill is runnable"
}

function Invoke-Run {
    param([string[]]$Arguments)

    Push-Location $IncludeDir
    try {
        & uv run python md_review_cli.py @Arguments
    } finally {
        Pop-Location
    }
}

$command = if ($args.Count -gt 0) { $args[0] } else { "help" }

switch ($command) {
    "help" { Show-Help }
    "validate" { Invoke-Validate }
    default { Invoke-Run -Arguments $args }
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall