@renoise/video-maker 0.1.3 → 0.2.0

package/.claude-plugin/marketplace.json

@@ -0,0 +1,15 @@
+{
+  "name": "renoise-plugins-official",
+  "owner": {
+    "name": "Renoise"
+  },
+  "description": "Official Claude Code plugins by Renoise",
+  "plugins": [
+    {
+      "name": "video-maker",
+      "version": "0.2.0",
+      "source": "./",
+      "description": "AI video production skills — creative direction, generation, editing, and e-commerce content"
+    }
+  ]
+}

package/.claude-plugin/plugin.json

@@ -1,5 +1,19 @@
 {
   "name": "video-maker",
-  "description": "Video production toolkit for AI video generation, e-commerce content, and more",
-  "version": "0.1.0"
-}
+  "description": "AI video production skills — creative direction, generation, editing, and e-commerce content",
+  "version": "0.2.0",
+  "author": {
+    "name": "Renoise"
+  },
+  "homepage": "https://github.com/ArcoCodes/renoise-plugins-official",
+  "repository": "https://github.com/ArcoCodes/renoise-plugins-official",
+  "keywords": [
+    "skills",
+    "video",
+    "ai-video",
+    "creative-direction",
+    "ecommerce",
+    "tiktok",
+    "renoise"
+  ]
+}

package/README.md

@@ -1,6 +1,20 @@
-# video-maker
+# renoise-plugins-official
 
-AI video production plugin for Claude Code. Install this plugin and get a creative director that turns your ideas into videos.
+AI video production skills by Renoise — creative direction, generation, editing, and e-commerce content.
+
+## Skills
+
+| Skill | Description |
+|-------|-------------|
+| **director** | Creative director — main entry point for all video requests |
+| **gemini-gen** | Visual understanding & multimodal analysis via Gemini 3.1 Pro |
+| **renoise-gen** | AI video & image generation engine (renoise-cli) |
+| **tiktok-content-maker** | TikTok & e-commerce short video specialist |
+| **scene-generate** | Background/environment image generation |
+| **product-sheet-generate** | Multi-angle product design sheet |
+| **short-film-editor** | Short film & drama editing |
+| **video-download** | Video downloader (yt-dlp) |
+| **file-upload** | Upload files to Renoise for use with gemini-gen |
 
 ## Installation
 
@@ -24,35 +38,8 @@ claude plugin install video-maker@renoise-plugins-official
 openclaw plugins install @renoise/video-maker
 ```
 
-## How It Works
-
-Just describe what you want — "make me a product video", "I want a short drama", "create a brand film" — and the **Director** skill takes over:
+## Environment Variables
 
-1. **Analyzes** your materials and creative brief
-2. **Suggests** 2-3 style directions tailored to your project
-3. **Generates** a complete video prompt, dialogue, and BGM plan
-4. **Submits** to Renoise for AI video generation
-5. **Learns** your preferences over time for better suggestions
-
-## Skills
-
-| Skill | Purpose |
-|-------|---------|
-| **director** | Creative director — the main entry point for all video requests |
-| renoise-gen | AI video & image generation engine (CLI) |
-| content-maker | TikTok e-commerce short video specialist |
-| scene-generate | Background/environment image generation (Gemini) |
-| product-sheet-generate | Multi-angle product design sheet (Gemini) |
-| video-download | Video downloader (yt-dlp) |
-
-## Adding New Verticals
-
-Create a new skill directory with a `SKILL.md` that includes a `categories` field in its frontmatter. The Director automatically discovers and routes to it — no other changes needed.
-
-```yaml
----
-name: my-vertical
-description: What this vertical handles
-categories: [drama, storytelling]
----
-```
+| Variable | Required By | Description |
+|----------|------------|-------------|
+| `RENOISE_API_KEY` | All skills | Renoise API credential. Get one at https://www.renoise.ai |

package/hooks/check-api-key.sh

@@ -0,0 +1,28 @@
+#!/usr/bin/env bash
+
+# PreToolUse hook: block when neither RENOISE_API_KEY nor RENOISE_AUTH_TOKEN is set
+# and the tool invocation looks like a renoise-cli call.
+
+set -euo pipefail
+
+# Read the tool input from stdin
+INPUT=$(cat)
+
+# Extract the command being executed
+COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command // empty')
+
+# Only check if the command involves renoise-cli
+if [[ "$COMMAND" != *renoise-cli* ]]; then
+  exit 0
+fi
+
+# If either credential is configured, allow
+if [ -n "${RENOISE_API_KEY:-}" ] || [ -n "${RENOISE_AUTH_TOKEN:-}" ]; then
+  exit 0
+fi
+
+# Block and guide user
+jq -n '{
+  decision: "block",
+  reason: "RENOISE_API_KEY or RENOISE_AUTH_TOKEN is not set. Add one to the env block in .claude/settings.local.json. Get your key at https://www.renoise.ai"
+}'

package/hooks/hooks.json

@@ -1,12 +1,12 @@
 {
   "hooks": {
-    "SessionStart": [
+    "PreToolUse": [
       {
-        "matcher": "*",
+        "matcher": "Bash",
         "hooks": [
           {
             "type": "command",
-            "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh",
+            "command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/check-api-key.sh",
             "timeout": 10
           }
         ]

package/openclaw.plugin.json

@@ -1,8 +1,8 @@
 {
   "id": "video-maker",
   "name": "Video Maker",
-  "description": "Video production toolkit for AI video generation, e-commerce content, and more",
-  "version": "0.1.2",
+  "description": "AI video production skills — creative direction, generation, editing, and e-commerce content",
+  "version": "0.2.0",
   "configSchema": {
     "type": "object",
     "additionalProperties": false,
@@ -10,11 +10,13 @@
   },
   "skills": [
     "skills/director",
+    "skills/gemini-gen",
     "skills/renoise-gen",
     "skills/tiktok-content-maker",
     "skills/scene-generate",
     "skills/product-sheet-generate",
+    "skills/short-film-editor",
     "skills/video-download",
-    "skills/short-film-editor"
+    "skills/file-upload"
   ]
 }

package/package.json

@@ -1,13 +1,12 @@
 {
   "name": "@renoise/video-maker",
-  "version": "0.1.3",
+  "version": "0.2.0",
   "license": "Apache-2.0",
   "type": "module",
-  "description": "Video production toolkit for AI video generation, e-commerce content, and more",
+  "description": "AI video production skills — creative direction, generation, editing, and e-commerce content",
   "repository": {
     "type": "git",
-    "url": "https://github.com/ArcoCodes/renoise-plugins-official.git",
-    "directory": "video-maker"
+    "url": "https://github.com/ArcoCodes/renoise-plugins-official.git"
   },
   "openclaw": {
     "extensions": ["./index.mjs"]
@@ -17,11 +16,7 @@
     "openclaw.plugin.json",
     "index.mjs",
     "hooks/",
-    "lib/",
     "skills/",
     "README.md"
-  ],
-  "dependencies": {
-    "@google/generative-ai": "^0.24.1"
-  }
+  ]
 }

package/skills/director/SKILL.md

@@ -6,8 +6,7 @@ description: >
   directions, generates video prompts, and submits video tasks. Use when
   user says "make a video", "video idea", "creative direction", "help me
   shoot", "I want a video", "video script", "storyboard", "generate video",
-  "action sequence", "做视频", "帮我拍", "视频创意", "短视频脚本", "分镜",
-  "生成视频". Do NOT use for downloading videos or editing existing footage.
+  "action sequence", "generate video". Do NOT use for downloading videos or editing existing footage.
   This skill is the ONLY entry point for video creation in the Visiono project.
 allowed-tools: Bash, Read
 metadata:
@@ -23,6 +22,7 @@ You are a creative director for AI video production. You guide users from raw id
 
 ## Critical Rules
 
+- **The Renoise platform URL is https://www.renoise.ai** — NEVER say or link to "renoise.com". The correct domain is `renoise.ai`.
 - **You are the default entry point** for ALL video creation requests. Only route to specialized skills when `metadata.tags` clearly match.
 - **Video prompts must be in English** — the model understands English best.
 - **Dialogue must feel natural** — conversational American English, never salesy or translated.
@@ -53,10 +53,7 @@ You are a creative director for AI video production. You guide users from raw id
    - What materials does the user have? (product photos, character refs, scripts, nothing)
    - What's the intended platform/audience? (TikTok, Instagram, YouTube, general)
 
-5. **If user provided product images**, analyze them:
-   ```bash
-   cd ${CLAUDE_PLUGIN_ROOT} && npm install --silent && npx tsx ${CLAUDE_PLUGIN_ROOT}/skills/tiktok-content-maker/scripts/analyze-images.ts <product-image> [model-image]
-   ```
+5. **If user provided product images**, analyze them using the `gemini-gen` skill — send product image(s) with a prompt to extract product type, colors, material, selling points, brand tone, and scene suggestions.
 
 6. **Present a brief summary**: "Here's what I understand: [product/story/concept]. I'll use [capabilities]. Let me suggest some creative directions."
 
@@ -226,7 +223,7 @@ Read that skill's SKILL.md and follow its workflow from the appropriate phase (s
 
 ### Example 1: Product video (common)
 User: "I have photos of my new sneakers, help me make a video"
-1. Phase 1: Analyze sneaker images via analyze-images.ts → extract product type, colors, selling points
+1. Phase 1: Analyze sneaker images via `gemini-gen` skill → extract product type, colors, selling points
 2. Phase 2: Suggest Minimal Showcase / Dynamic Sports / Lifestyle Vlog with adapted descriptions
 3. User picks "Dynamic Sports"
 4. Phase 3: Generate 15s video prompt with fast tracking, high-energy BGM, beat-synced cuts

package/skills/file-upload/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: file-upload
+description: >
+  Upload files (images, videos) to Renoise and get a file URI for use with gemini-gen.
+  Use when a file exceeds 20MB inline base64 limit, or when you need to reuse
+  the same file across multiple gemini-gen calls without re-encoding.
+allowed-tools: Bash, Read
+metadata:
+  author: renoise
+  version: 0.1.0
+  category: utility
+  tags: [upload, file, gemini]
+---
+
+# File Upload
+
+Upload files via the Renoise gateway and get back a file URI for use with `gemini-gen`.
+
+## When to Use
+
+- File exceeds 20MB (inline base64 limit for `gemini-gen`)
+- Same file needs to be referenced in multiple `gemini-gen` calls (upload once, reuse URI)
+
+## Prerequisites
+
+- `RENOISE_API_KEY` environment variable set
+
+## API
+
+```
+POST https://staging.renoise.ai/api/public/v1/llm/files/upload
+Header: X-API-Key: <RENOISE_API_KEY>
+Body: multipart/form-data with field "file"
+```
+
+## CLI Script
+
+```bash
+# Upload a file, get back a file URI
+node ${CLAUDE_SKILL_DIR}/scripts/upload.mjs <file-path>
+
+# Capture URI for use with gemini-gen
+FILE_URI=$(node ${CLAUDE_SKILL_DIR}/scripts/upload.mjs large-video.mp4)
+```
+
+Progress messages go to stderr, the file URL goes to stdout.
+
+## Response Format
+
+```json
+{
+  "previewUrl": "https://...r2.cloudflarestorage.com/.../filename?X-Amz-...",
+  "mimeType": "image/jpeg",
+  "size": 111198,
+  "expiresAt": "2026-03-26T11:49:07.328Z"
+}
+```
+
+- `previewUrl` — Signed URL, valid for **1 hour**
+- Upload once, use the URL immediately in downstream skills
+
+## Usage with gemini-gen
+
+```bash
+# Step 1: Upload
+FILE_URL=$(node ${CLAUDE_PLUGIN_ROOT}/skills/file-upload/scripts/upload.mjs large-video.mp4)
+
+# Step 2: Use with gemini-gen
+node ${CLAUDE_PLUGIN_ROOT}/skills/gemini-gen/scripts/gemini.mjs \
+  --file-uri "$FILE_URL" --file-mime video/mp4 \
+  "Analyze this video"
+```
+
+## Supported File Types
+
+Images: `.jpg`, `.jpeg`, `.png`, `.webp`, `.gif`
+Videos: `.mp4`, `.mov`, `.webm`
+Audio: `.mp3`, `.wav`
+Documents: `.pdf`

package/skills/file-upload/scripts/upload.mjs

@@ -0,0 +1,103 @@
+#!/usr/bin/env node
+
+/**
+ * Upload a file via Renoise gateway for use with gemini-gen.
+ * Outputs the file URI to stdout.
+ *
+ * Usage: node upload.mjs <file-path>
+ *
+ * Environment:
+ *   RENOISE_API_KEY  Required. Get one at https://www.renoise.ai
+ */
+
+import fs from "fs/promises";
+import path from "path";
+
+const RENOISE_API_KEY = process.env.RENOISE_API_KEY;
+if (!RENOISE_API_KEY) {
+  console.error("RENOISE_API_KEY not set. Get one at: https://www.renoise.ai");
+  process.exit(1);
+}
+
+const UPLOAD_ENDPOINT =
+  "https://staging.renoise.ai/api/public/v1/llm/files/upload";
+
+const MIME_MAP = {
+  ".jpg": "image/jpeg",
+  ".jpeg": "image/jpeg",
+  ".png": "image/png",
+  ".webp": "image/webp",
+  ".gif": "image/gif",
+  ".mp4": "video/mp4",
+  ".mov": "video/quicktime",
+  ".webm": "video/webm",
+  ".mp3": "audio/mpeg",
+  ".wav": "audio/wav",
+  ".pdf": "application/pdf",
+};
+
+function getMimeType(filePath) {
+  return (
+    MIME_MAP[path.extname(filePath).toLowerCase()] ?? "application/octet-stream"
+  );
+}
+
+async function main() {
+  const filePath = process.argv[2];
+  if (!filePath) {
+    console.error("Usage: node upload.mjs <file-path>");
+    process.exit(1);
+  }
+
+  const stat = await fs.stat(filePath).catch(() => {
+    console.error(`File not found: ${filePath}`);
+    process.exit(1);
+  });
+
+  const mimeType = getMimeType(filePath);
+  const fileData = await fs.readFile(filePath);
+  const fileName = path.basename(filePath);
+
+  console.error(
+    `Uploading ${fileName} (${(stat.size / 1024 / 1024).toFixed(1)}MB, ${mimeType})...`
+  );
+
+  // Build multipart form-data with native FormData + Blob
+  const blob = new Blob([fileData], { type: mimeType });
+  const form = new FormData();
+  form.append("file", blob, fileName);
+
+  const res = await fetch(UPLOAD_ENDPOINT, {
+    method: "POST",
+    headers: {
+      "X-API-Key": RENOISE_API_KEY,
+    },
+    body: form,
+  });
+
+  if (!res.ok) {
+    const errText = await res.text();
+    console.error(`Upload error ${res.status}: ${errText}`);
+    process.exit(1);
+  }
+
+  const data = await res.json();
+
+  // Response format: { previewUrl, mimeType, size, expiresAt }
+  const fileUrl = data?.previewUrl;
+
+  if (!fileUrl) {
+    console.error("No previewUrl in response:", JSON.stringify(data, null, 2));
+    process.exit(1);
+  }
+
+  const expires = data.expiresAt ? new Date(data.expiresAt).toLocaleString() : "unknown";
+  console.error(`Uploaded: ${(data.size / 1024).toFixed(0)}KB, expires ${expires}`);
+  // Print URL to stdout (stderr used for progress messages)
+  console.log(fileUrl);
+}
+
+main().catch((err) => {
+  console.error("ERROR:", err.message);
+  process.exit(1);
+});

package/skills/gemini-gen/SKILL.md

@@ -0,0 +1,232 @@
+---
+name: gemini-gen
+description: >
+  Visual understanding and multimodal analysis via Gemini 3.1 Pro.
+  Use when you need to understand, analyze, or extract information from images or videos:
+  analyze product photos, extract video scripts/dialogue, understand video content for replication,
+  compare visual assets, OCR/text extraction from images, describe scenes for prompt writing,
+  extract style/color/composition from reference footage.
+  Do NOT use for generating images or videos — use renoise-gen instead.
+allowed-tools: Bash, Read
+metadata:
+  author: renoise
+  version: 0.2.0
+  category: ai-foundation
+  tags: [vision, analysis, multimodal, gemini]
+---
+
+# Gemini Gen — Visual Understanding & Multimodal Analysis
+
+Gemini 3.1 Pro via Renoise gateway. Zero npm dependencies, native `fetch` only.
+
+## When to Use
+
+| Scenario | Example |
+|----------|---------|
+| **Analyze product photos** | Extract type, color, material, selling points, brand tone from product images |
+| **Understand video content** | "What happens in this video?", summarize scenes, identify actions and objects |
+| **Extract scripts from video** | Watch a reference video → output timestamped dialogue, scene descriptions, camera movements |
+| **Replicate a video style** | Analyze a reference clip → extract visual style, pacing, transitions, color grading for recreation |
+| **Compare visual assets** | Side-by-side analysis of two product photos, before/after comparison |
+| **OCR / text extraction** | Read text from screenshots, packaging, signage in images |
+| **Describe scenes for prompts** | Look at a reference image → write a detailed prompt for `renoise-gen` to recreate the style |
+| **Content review** | Check if generated output matches the creative brief |
+
+## When NOT to Use
+
+- **Generating images** → use `renoise-gen` with `nano-banana-2`
+- **Generating videos** → use `renoise-gen` with `renoise-2.0`
+- **Uploading large files** → use `file-upload` first, then pass the URL here
+
+## Authentication
+
+Use environment variable `RENOISE_API_KEY`. Get one at: https://www.renoise.ai
+
+## API Endpoint
+
+```
+POST https://staging--ujgsvru36x4korjj10nq.edgespark.app/api/public/llm/proxy/v1beta/models/{model}:generateContent?key={RENOISE_API_KEY}
+```
+
+Default model: `gemini-3.1-pro`
+
+## Request Format
+
+```json
+{
+  "contents": [
+    {
+      "role": "user",
+      "parts": [{ "text": "your prompt here" }]
+    }
+  ],
+  "generationConfig": {
+    "temperature": 1.0,
+    "maxOutputTokens": 8192
+  }
+}
+```
+
+## Multimodal Input (images & videos)
+
+Gemini supports images and videos as inline base64 parts alongside text. Multiple files can be sent in the same request.
+
+### Image Input
+
+```json
+{
+  "contents": [
+    {
+      "parts": [
+        {
+          "inlineData": {
+            "mimeType": "image/jpeg",
+            "data": "<base64-encoded-data>"
+          },
+          "mediaResolution": { "level": "media_resolution_high" }
+        },
+        { "text": "Describe this image" }
+      ]
+    }
+  ]
+}
+```
+
+`mediaResolution` controls token allocation per image/frame:
+
+| Level | Image Tokens | Video Frame Tokens |
+|-------|-------------|-------------------|
+| `media_resolution_low` | 280 | 70 |
+| `media_resolution_medium` | 560 | 140 |
+| `media_resolution_high` | 840 | 210 |
+| `media_resolution_ultra_high` | 1120 | 280 |
+
+Default: `media_resolution_medium`. Use `high` or `ultra_high` for detail-critical analysis (product photos, fine text). Use `low` for bulk/batch processing.
+
+### Video Input
+
+Same format — just use a video MIME type. Inline base64 has a **20MB limit**. For larger videos, use the dedicated file upload skill.
+
+```json
+{
+  "contents": [
+    {
+      "parts": [
+        {
+          "inlineData": {
+            "mimeType": "video/mp4",
+            "data": "<base64-encoded-data>"
+          },
+          "mediaResolution": { "level": "media_resolution_low" }
+        },
+        { "text": "Summarize what happens in this video" }
+      ]
+    }
+  ]
+}
+```
+
+> **Tip**: Use `media_resolution_low` for videos to reduce token consumption — video has many frames.
+
+### Multiple Files
+
+Send multiple images/videos in one request by adding more `inlineData` parts:
+
+```json
+{
+  "contents": [
+    {
+      "parts": [
+        { "inlineData": { "mimeType": "image/jpeg", "data": "<base64-image-1>" } },
+        { "inlineData": { "mimeType": "image/png", "data": "<base64-image-2>" } },
+        { "text": "Compare these two product photos" }
+      ]
+    }
+  ]
+}
+```
+
+### Large Files (> 20MB)
+
+Inline base64 has a **20MB limit**. For larger files, use the dedicated file upload skill to get a file URI, then reference it:
+
+```json
+{
+  "contents": [
+    {
+      "parts": [
+        {
+          "fileData": {
+            "mimeType": "video/mp4",
+            "fileUri": "<uploaded-file-uri>"
+          }
+        },
+        { "text": "Analyze this video" }
+      ]
+    }
+  ]
+}
+```
+
+## Supported MIME Types
+
+| Extension  | MIME Type       | Max Inline |
+| ---------- | --------------- | ---------- |
+| .jpg/.jpeg | image/jpeg      | 20MB       |
+| .png       | image/png       | 20MB       |
+| .webp      | image/webp      | 20MB       |
+| .gif       | image/gif       | 20MB       |
+| .mp4       | video/mp4       | 20MB       |
+| .mov       | video/quicktime | 20MB       |
+| .webm      | video/webm      | 20MB       |
+
+## Response Parsing
+
+```javascript
+const data = await response.json();
+const text = data.candidates[0].content.parts[0].text;
+```
+
+## Error Handling
+
+- 400: Bad request (check prompt format)
+- 403: Invalid API key
+- 429: Rate limited (wait and retry)
+- 500: Server error (retry with backoff)
+
+## CLI Script
+
+`${CLAUDE_SKILL_DIR}/scripts/gemini.mjs` — zero-dependency Node.js script, other skills can directly call it.
+
+```bash
+# Text only
+node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs "Explain quantum computing"
+
+# Analyze an image (high resolution for product detail)
+node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file photo.jpg --resolution high "Describe this product"
+
+# Analyze a video (low resolution to save tokens)
+node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file clip.mp4 --resolution low "Summarize this clip"
+
+# Multiple images
+node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file a.jpg --file b.jpg "Compare these two"
+
+# Uploaded file URI (from file upload skill, for files > 20MB)
+node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --file-uri "<uri>" --file-mime video/mp4 "Analyze this video"
+
+# JSON output mode
+node ${CLAUDE_SKILL_DIR}/scripts/gemini.mjs --json "Return a JSON object with name and age"
+```
+
+### Options
+
+| Flag | Default | Description |
+|------|---------|-------------|
+| `--file <path>` | — | Attach local file (repeatable) |
+| `--file-uri <uri>` | — | Attach uploaded file by URI (requires `--file-mime`) |
+| `--file-mime <mime>` | — | MIME type for `--file-uri` |
+| `--resolution <level>` | `medium` | `low` / `medium` / `high` / `ultra_high` |
+| `--model <name>` | `gemini-3.1-pro` | Model name |
+| `--temperature <n>` | `1.0` | Temperature |
+| `--max-tokens <n>` | `8192` | Max output tokens |
+| `--json` | off | Request JSON response format |