media-gen-cli 1.5.0

package/package.json

@@ -0,0 +1,63 @@
+{
+  "name": "media-gen-cli",
+  "version": "1.5.0",
+  "description": "Production-ready CLI for multi-provider media generation (images, video, voice, audio) designed for developers and AI agents",
+  "type": "module",
+  "main": "./dist/media-gen.js",
+  "bin": {
+    "media-gen": "./dist/media-gen.mjs"
+  },
+  "files": [
+    "dist/media-gen.mjs",
+    "skills/",
+    "README.md",
+    "LICENSE",
+    ".env.example"
+  ],
+  "scripts": {
+    "dev": "tsx src/index.ts",
+    "build": "node esbuild.config.mjs",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "lint": "eslint src/ --ext .ts",
+    "format": "prettier --write \"src/**/*.ts\"",
+    "typecheck": "tsc --noEmit",
+    "prepublishOnly": "npm run build"
+  },
+  "keywords": [
+    "ai",
+    "media-generation",
+    "image-generation",
+    "video-generation",
+    "text-to-speech",
+    "transcription",
+    "openai",
+    "gemini",
+    "elevenlabs",
+    "deepgram",
+    "cli"
+  ],
+  "author": "Francis Hor <francishoe@gmail.com>",
+  "license": "MIT",
+  "engines": {
+    "node": ">=18.0.0"
+  },
+  "dependencies": {
+    "commander": "^12.1.0",
+    "dotenv": "^16.4.7",
+    "edge-tts-universal": "^1.4.0",
+    "ora": "^8.1.1",
+    "pino": "^9.6.0",
+    "pino-pretty": "^13.0.0",
+    "zod": "^3.24.1"
+  },
+  "devDependencies": {
+    "@types/node": "^22.10.0",
+    "esbuild": "^0.24.2",
+    "eslint": "^9.16.0",
+    "prettier": "^3.4.2",
+    "tsx": "^4.19.2",
+    "typescript": "^5.7.2",
+    "vitest": "^2.1.8"
+  }
+}

package/skills/media-generation/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Francis Hor
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/skills/media-generation/RELEASE_NOTES.md

@@ -0,0 +1,98 @@
+# Release Notes
+
+## v1.5.0 (2026-07-09)
+
+### New Capabilities
+- **OpenRouter video generation** — 12 models via `POST /api/v1/videos` (async with polling)
+  - google/veo-3.1, google/veo-3.1-fast, google/veo-3.1-lite
+  - alibaba/happy-horse-1.1, alibaba/happy-horse-1.0, alibaba/wan-2.7
+  - x-ai/grok-imagine-video
+  - kuaishou/kling-video-3.0-pro, kuaishou/kling-video-3.0-standard
+  - minimax/hailuo-2.3
+  - bytedance-seed/seedance-2.0-fast, bytedance-seed/seedance-2.0
+- **OpenRouter image** — added microsoft/mai-image-2.5
+- Auto-generate `~/.media-gen/.env` template on first run (all keys commented out)
+- `--version` now reflects package.json (injected at build time)
+- `.plugin/plugin.json` for Open Plugins standard (cursor.directory compatibility)
+- `npx skills add onimusya/media-gen` installation support
+
+### Fixes
+- Fixed OpenRouter video endpoint (`POST /api/v1/videos`, not `/video/generations`)
+- Fixed OpenRouter video download (uses `unsigned_urls[]` with auth header)
+- Fixed `~/.media-gen/logs/` not created on `--help` or `--version`
+- Fixed `--version` showing hardcoded `1.0.0`
+
+## v1.3.0 (2026-07-08)
+
+### New Capabilities
+- **Runway image generation** — gen4_image, gen4_image_turbo, gemini_image3_pro, gemini_image3.1_flash, gemini_2.5_flash, gpt_image_2
+- **Runway multi-provider video** — veo3, veo3.1, seedance2, seedance2_fast, seedance2_mini, happyhorse_1_0, gemini_omni_flash (text-to-video + image-to-video)
+- **Deepgram TTS** — Aura-2 and Aura models with 19 featured voices (English, German, Italian, Japanese)
+
+### Updated Models
+- **Runway**: expanded from 5 to 18 models (image + video + image-to-video)
+- **Deepgram**: added `aura-2` and `aura` TTS models with voice IDs (e.g., `aura-2-thalia-en`)
+- **Fal.ai**: added ByteDance Seedream v5/v4, Dreamina v3.1, all Seedance 2.0 variants (standard/fast/mini)
+
+### Fixes
+- Fixed Fal.ai queue status/download URL construction (strips endpoint suffix for queue paths)
+- Fixed Azure provider to use Azure AI Services OpenAI-compatible endpoint format
+
+## v1.2.0 (2026-07-08)
+
+### Changes
+- **Azure provider rewritten** for Azure AI Services OpenAI-compatible endpoint (`https://{resource}.services.ai.azure.com/openai/v1`)
+- Azure models: gpt-image-2, gpt-image-1.5, gpt-4o-mini-tts with 13 voice IDs
+- Added `LICENSE` and `RELEASE_NOTES.md` to skills folder
+- Added prerequisites section to README
+- Added ByteDance Seedream v5/v4 and Dreamina v3.1 for Fal.ai
+- Added all Seedance 2.0 variants for Fal.ai (text-to-video, fast, mini)
+
+## v1.1.0 (2026-07-07)
+
+### New Providers
+- **MiniMax (Hailuo)** — video generation (Hailuo 2.3, 2.3Fast, 02) + TTS (speech-2.8-hd/turbo)
+- **Google Gemini TTS** — 30 voices, controllable style, 3 models (gemini-3.1-flash-tts-preview, gemini-2.5-flash-preview-tts, gemini-2.5-pro-preview-tts)
+
+### New Features
+- `--instructions` option for OpenAI/Azure TTS (gpt-4o-mini-tts) to control voice style, tone, accent
+- `MEDIA_GEN_VOICE_ID` env var — set default voice-id so `--voice-id` is optional
+- `MEDIA_GEN_LOG_LEVEL` env var — configurable log level (silent/error/warn/info/debug/trace)
+- Structured logging to `~/.media-gen/logs/media-gen-YYYY-MM-DD.log`
+- Minified + obfuscated production build (519KB)
+- Release scripts (`scripts/release.sh`, `scripts/release.ps1`)
+- `config init --global` for user-level setup at `~/.media-gen/`
+
+### Fixes
+- Fixed Fal.ai queue status/download URL construction (model path stripping for Seedance 2.0)
+- Fixed home `~/.media-gen/.env` loading — now properly overrides stale system env vars
+- Fixed Google Veo API: correct model names (`veo-3.1-generate-preview`), auth headers (`x-goog-api-key`), job polling URLs
+- Azure provider rewritten to use Azure AI Services OpenAI-compatible endpoint
+
+### Updated Models
+- **OpenAI**: gpt-image-2, 13 voice IDs (alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer, verse, marin, cedar)
+- **Azure**: gpt-image-2, gpt-image-1.5, gpt-4o-mini-tts, 13 voice IDs
+- **ElevenLabs**: 21 premade voice IDs (fetched from live API, free plan)
+- **Google**: imagen-4.0, veo-3.1 variants, 30 TTS voices (Kore, Puck, Zephyr, etc.)
+- **Fal.ai**: Seedance 2.0 (standard/fast/mini), Seedream v5/v4, Dreamina v3.1
+- **Deepgram**: nova-3, nova-3-medical
+- **Luma**: ray3.2, ray3.14
+- **Runway**: gen4.5, aleph-2.0
+- **Replicate**: flux-2-pro/max, flux-kontext-pro, gen-4.5, happy-horse-1.0
+- **OpenRouter**: gpt-image-2, gemini-3.1-flash-image, grok-imagine, flux.2-klein-4b
+
+## v1.0.0 (2026-07-06)
+
+### Initial Release
+- 13 provider adapters: OpenAI, Google, Azure, ElevenLabs, Deepgram, Fal.ai, Luma AI, Replicate, Stability AI, Runway, OpenRouter, MiniMax, Edge TTS (free)
+- CLI commands: image generate/edit, video generate/image-to-video/extend, voice tts/clone/isolate, audio transcribe/translate
+- AI agent SKILL.md following Agent Skills open standard
+- Default provider/model/voice-id via env vars
+- Multi-level config: `~/.media-gen/.env` → project `.env` → env vars
+- `models.json` config for model/voice registry (bundled + user override at `.media-gen/models.json`)
+- Cross-platform scripts (bash, cmd, PowerShell)
+- Single bundled JS file via esbuild
+- Async video job polling with `--wait`, `--poll-interval`, `--timeout`
+- Structured JSON output (`--json`) for agent integration
+- Dry-run mode (`--dry-run`) for cost-safe validation
+- 25 tests passing

package/skills/media-generation/SKILL.md

@@ -0,0 +1,273 @@
+---
+name: media-generation
+description: Generate and edit images, create videos, synthesize speech, transcribe and translate audio using multiple AI providers (OpenAI, Google, ElevenLabs, Deepgram, Fal, Luma, Replicate, Stability, Runway, OpenRouter, Edge TTS). Use when the user asks to create media assets, generate pictures, make videos, produce voiceovers, transcribe recordings, or work with any visual/audio content.
+compatibility: Requires Node.js 18+ and at least one provider API key configured in .env (Edge TTS is free, no key needed)
+metadata:
+  author: Francis Hor <francishoe@gmail.com>
+  version: "1.0"
+allowed-tools: Bash(node:*)
+---
+
+# Media Generation
+
+Run the CLI at `${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs` with Node.js. Always use `--json` for parseable output.
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs <command> [options] --json
+```
+
+## Commands
+
+| Command | Purpose |
+|---------|---------|
+| `image generate` | Generate images from text prompts |
+| `image edit` | Edit existing images with a prompt |
+| `video generate` | Generate video from text (async) |
+| `video image-to-video` | Animate an image into video |
+| `video extend` | Extend an existing video |
+| `voice tts` | Text to speech synthesis |
+| `voice clone` | Clone a voice from audio samples |
+| `voice isolate` | Isolate voice from background audio |
+| `audio transcribe` | Transcribe audio to text |
+| `audio translate` | Translate audio to another language |
+| `providers list` | List all providers with capabilities, models, and voices |
+| `providers list --configured` | List only configured providers |
+| `providers list --capability <cap>` | Filter by capability |
+| `providers models` | List all models across all providers |
+| `providers models --provider <id>` | List models/voices for a specific provider |
+| `providers models --capability <cap>` | Filter models by capability |
+| `config init` | Initialize project-level config |
+| `config init --global` | Initialize user-level config at ~/.media-gen/ |
+| `config validate` | Check which providers are configured |
+| `job status` | Check async job status |
+| `job download` | Download completed async job result |
+
+## Configuration
+
+Defaults are set via `.env` (at project root or `~/.media-gen/.env` for global). With defaults configured, `--provider`, `--model`, and `--voice-id` are all optional:
+
+```bash
+MEDIA_GEN_DEFAULT_PROVIDER=openrouter
+MEDIA_GEN_DEFAULT_MODEL=openai/gpt-image-2
+MEDIA_GEN_VOICE_PROVIDER=edge-tts
+MEDIA_GEN_VOICE_MODEL=
+MEDIA_GEN_VOICE_ID=en-US-EmmaMultilingualNeural
+MEDIA_GEN_VIDEO_PROVIDER=google
+MEDIA_GEN_VIDEO_MODEL=veo-3.1-generate-preview
+MEDIA_GEN_AUDIO_PROVIDER=deepgram
+MEDIA_GEN_AUDIO_MODEL=nova-3
+MEDIA_GEN_LOG_LEVEL=error
+```
+
+## Examples
+
+### Image generation
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs image generate \
+  --prompt "A pixel art fantasy arena" \
+  --output ./outputs/arena.png \
+  --json
+```
+
+### Video generation (wait for result)
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs video generate \
+  --provider google \
+  --model veo-3.1-generate-preview \
+  --prompt "A cinematic card pack opening" \
+  --duration 8 \
+  --output ./outputs/video.mp4 \
+  --wait \
+  --json
+```
+
+### Text to speech (Edge TTS - free, no API key)
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs voice tts \
+  --provider edge-tts \
+  --voice-id en-US-EmmaMultilingualNeural \
+  --text "Hello world" \
+  --output ./outputs/voice.mp3 \
+  --json
+```
+
+### Text to speech (ElevenLabs)
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs voice tts \
+  --provider elevenlabs \
+  --voice-id JBFqnCBsd6RMkjVDRZzb \
+  --text "Welcome to the show" \
+  --output ./outputs/george.mp3 \
+  --json
+```
+
+### Text to speech (Google Gemini TTS)
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs voice tts \
+  --provider google \
+  --model gemini-3.1-flash-tts-preview \
+  --voice-id Kore \
+  --text "Say cheerfully: Have a wonderful day!" \
+  --output ./outputs/gemini-voice.wav \
+  --json
+```
+
+### Text to speech (OpenAI)
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs voice tts \
+  --provider openai \
+  --model gpt-4o-mini-tts \
+  --voice-id coral \
+  --text "Hello from OpenAI" \
+  --output ./outputs/openai-voice.mp3 \
+  --json
+```
+
+### Text to speech (with defaults set, minimal)
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs voice tts \
+  --text "Just provide text when defaults are configured" \
+  --output ./outputs/speech.mp3 \
+  --json
+```
+
+### Transcription
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs audio transcribe \
+  --input ./audio/recording.mp3 \
+  --output ./outputs/transcript.json \
+  --json
+```
+
+### List supported providers and models
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs providers list --json
+```
+
+### List voices for a TTS provider
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs providers models --provider edge-tts --json
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs providers models --provider elevenlabs --json
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs providers models --provider openai --json
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs providers models --provider google --json
+```
+
+### Dry run (validate without calling API)
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs image generate \
+  --prompt "test" --dry-run --json
+```
+
+## Async Video Jobs
+
+Video generation is asynchronous. Providers return a job ID instead of a file.
+
+### Pattern 1: Wait for completion (simple)
+
+Add `--wait` to block until the video is ready:
+
+```bash
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs video generate \
+  --provider google \
+  --model veo-3.1-generate-preview \
+  --prompt "A cinematic scene" \
+  --output ./outputs/video.mp4 \
+  --wait \
+  --poll-interval 5000 \
+  --timeout 300000 \
+  --json
+```
+
+Returns the final file path when complete.
+
+### Pattern 2: Non-blocking (get job ID, check later)
+
+Without `--wait`, the CLI returns immediately with a job ID:
+
+```bash
+# Start generation (returns instantly)
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs video generate \
+  --provider google \
+  --model veo-3.1-generate-preview \
+  --prompt "A cinematic scene" \
+  --json
+# Returns: {"ok": true, "jobId": "operations/abc123", "status": "processing"}
+
+# Check status later
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs job status \
+  --provider google \
+  --job-id "operations/abc123" \
+  --json
+# Returns: {"ok": true, "jobId": "...", "status": "completed"}
+
+# Download the result
+node ${CLAUDE_SKILL_DIR}/scripts/media-gen.mjs job download \
+  --provider google \
+  --job-id "operations/abc123" \
+  --output ./outputs/video.mp4 \
+  --json
+```
+
+### Async options
+
+| Option | Default | Description |
+|--------|---------|-------------|
+| `--wait` | false | Block until job completes |
+| `--poll-interval` | 5000 | Milliseconds between status checks |
+| `--timeout` | 600000 | Max wait time (10 minutes) |
+
+### Async providers
+
+Google (Veo), Luma AI, Runway, Fal.ai, and Replicate all use async for video. Image and TTS are always synchronous.
+
+## Response format
+
+Success:
+```json
+{"ok": true, "type": "image", "provider": "openai", "model": "gpt-image-2", "outputFile": "./outputs/image.png", "durationMs": 1200}
+```
+
+Error:
+```json
+{"ok": false, "error": {"code": "PROVIDER_NOT_CONFIGURED", "message": "Missing OPENAI_API_KEY", "suggestion": "Set OPENAI_API_KEY in .env"}}
+```
+
+## Rules
+
+- Use `--json` for all calls.
+- Use `--dry-run` before expensive operations when unsure.
+- Never use `--overwrite` unless the user confirms.
+- Keep outputs inside the project workspace.
+- For video, use `--wait` only when the user wants the file immediately.
+- Check the `ok` field in every response before proceeding.
+- On error, show the `suggestion` field to the user.
+- For TTS, `--voice-id` is optional when `MEDIA_GEN_VOICE_ID` is set in .env.
+- Edge TTS is free and requires no API key — prefer it for basic TTS tasks.
+
+## Provider Capabilities
+
+| Provider | Image | Video | TTS | Transcribe | Translate | Clone | Isolate |
+|----------|-------|-------|-----|------------|-----------|-------|---------|
+| openai | Yes | | Yes | Yes | Yes | | |
+| google | Yes | Yes | Yes | | | | |
+| azure | Yes | | Yes | Yes | Yes | | |
+| elevenlabs | | | Yes | | | Yes | Yes |
+| deepgram | | | Yes | Yes | Yes | | |
+| fal | Yes | Yes | | | | | |
+| luma | | Yes | | | | | |
+| replicate | Yes | Yes | | | | | |
+| stability | Yes | | | | | | |
+| runway | | Yes | | | | | |
+| openrouter | Yes | Yes | | | | | |
+| edge-tts | | | Yes (free) | | | | |

package/skills/media-generation/scripts/install.cmd

@@ -0,0 +1,46 @@
+@echo off
+REM Install media-gen-cli (Windows CMD)
+setlocal enabledelayedexpansion
+
+set "SCRIPT_DIR=%~dp0"
+pushd "%SCRIPT_DIR%\..\..\..\"
+set "PROJECT_DIR=%CD%"
+popd
+
+echo Installing media-gen-cli from: %PROJECT_DIR%
+
+cd /d "%PROJECT_DIR%"
+
+REM Check for Node.js
+where node >nul 2>&1
+if %ERRORLEVEL% neq 0 (
+    echo Error: Node.js is required but not installed.
+    echo Install it from https://nodejs.org/ ^(v18+^)
+    exit /b 1
+)
+
+REM Install dependencies
+echo Installing dependencies...
+call npm install --silent
+if %ERRORLEVEL% neq 0 exit /b 1
+
+REM Build the CLI
+echo Building CLI...
+call npm run build --silent
+if %ERRORLEVEL% neq 0 exit /b 1
+
+REM Verify
+if exist "%PROJECT_DIR%\dist\media-gen.mjs" (
+    echo.
+    echo [OK] media-gen-cli installed successfully!
+    echo.
+    echo Run with:
+    echo   node %PROJECT_DIR%\dist\media-gen.mjs --help
+    echo.
+    echo Or link globally:
+    echo   npm link
+    echo   media-gen --help
+) else (
+    echo Error: Build failed. dist\media-gen.mjs not found.
+    exit /b 1
+)

package/skills/media-generation/scripts/install.ps1

@@ -0,0 +1,58 @@
+# Install media-gen-cli (Windows PowerShell)
+# Compatible with PowerShell 5.1+ and PowerShell Core 7+
+$ErrorActionPreference = "Stop"
+
+$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
+$ProjectDir = Resolve-Path (Join-Path $ScriptDir "..\..\..") | Select-Object -ExpandProperty Path
+
+Write-Host "Installing media-gen-cli from: $ProjectDir"
+
+Set-Location $ProjectDir
+
+# Check for Node.js
+try {
+    $nodeVersion = & node -v 2>$null
+} catch {
+    Write-Host "Error: Node.js is required but not installed." -ForegroundColor Red
+    Write-Host "Install it from https://nodejs.org/ (v18+)"
+    exit 1
+}
+
+if (-not $nodeVersion) {
+    Write-Host "Error: Node.js is required but not installed." -ForegroundColor Red
+    Write-Host "Install it from https://nodejs.org/ (v18+)"
+    exit 1
+}
+
+$major = [int]($nodeVersion -replace 'v(\d+)\..*', '$1')
+if ($major -lt 18) {
+    Write-Host "Error: Node.js 18+ is required. Found: $nodeVersion" -ForegroundColor Red
+    exit 1
+}
+
+# Install dependencies
+Write-Host "Installing dependencies..."
+& npm install --silent
+if ($LASTEXITCODE -ne 0) { exit 1 }
+
+# Build the CLI
+Write-Host "Building CLI..."
+& npm run build --silent
+if ($LASTEXITCODE -ne 0) { exit 1 }
+
+# Verify
+$distPath = Join-Path $ProjectDir "dist\media-gen.mjs"
+if (Test-Path $distPath) {
+    Write-Host ""
+    Write-Host "media-gen-cli installed successfully!" -ForegroundColor Green
+    Write-Host ""
+    Write-Host "Run with:"
+    Write-Host "  node $distPath --help"
+    Write-Host ""
+    Write-Host "Or link globally:"
+    Write-Host "  npm link"
+    Write-Host "  media-gen --help"
+} else {
+    Write-Host "Error: Build failed. dist\media-gen.mjs not found." -ForegroundColor Red
+    exit 1
+}

package/skills/media-generation/scripts/install.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+# Install media-gen-cli
+# Compatible with Linux, macOS, and Windows (Git Bash/WSL)
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+PROJECT_DIR="$(cd "$SCRIPT_DIR/../../.." && pwd)"
+
+echo "Installing media-gen-cli from: $PROJECT_DIR"
+
+cd "$PROJECT_DIR"
+
+# Check for Node.js
+if ! command -v node &> /dev/null; then
+  echo "Error: Node.js is required but not installed."
+  echo "Install it from https://nodejs.org/ (v18+)"
+  exit 1
+fi
+
+NODE_VERSION=$(node -v | cut -d'v' -f2 | cut -d'.' -f1)
+if [ "$NODE_VERSION" -lt 18 ]; then
+  echo "Error: Node.js 18+ is required. Found: $(node -v)"
+  exit 1
+fi
+
+# Install dependencies
+echo "Installing dependencies..."
+npm install --silent
+
+# Build the CLI
+echo "Building CLI..."
+npm run build --silent
+
+# Verify
+if [ -f "$PROJECT_DIR/dist/media-gen.mjs" ]; then
+  echo ""
+  echo "✓ media-gen-cli installed successfully!"
+  echo ""
+  echo "Run with:"
+  echo "  node $PROJECT_DIR/dist/media-gen.mjs --help"
+  echo ""
+  echo "Or link globally:"
+  echo "  npm link"
+  echo "  media-gen --help"
+else
+  echo "Error: Build failed. dist/media-gen.mjs not found."
+  exit 1
+fi

package/skills/media-generation/scripts/media-gen.cmd

@@ -0,0 +1,3 @@
+@echo off
+REM media-gen CLI runner (Windows CMD)
+node "%~dp0media-gen.mjs" %*