A conversation-driven assistant for batch AI video and image generation that integrates with local client interfaces.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ai-productivity-assistant
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ai-productivity-assistant using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is AI Video & Image Productivity Assistant?
The AI Productivity Tool Assistant is a sophisticated bridge between conversational AI agents and local media generation engines. It allows developers and creators to trigger high-quality video and image production workflows through simple natural language commands. By utilizing Openclaw Skills, this tool communicates directly with a local client running on a loopback address, removing the need for complex API key management and allowing for secure, localized control over the creative process.
This skill is designed to handle professional-grade models including Sora for video synthesis, Veo for high-definition cinematic content, and Nano Banana for ultra-clear image generation. It supports various input methods, from text-to-video to complex image-to-video tasks with reference frames, making it a versatile asset for any content production pipeline.
AI Video & Image Productivity Assistant Use Cases
- Creating marketing videos from 10 to 25 seconds using Sora landscape or portrait models.
- Batch processing product photography by converting standard images into 4K stylized visuals.
- Automating social media content creation through mobile chat platforms like WeChat or Lark.
- Generating cinematic video loops from static images using Veo reference frame technology.
- Tracking and managing multiple high-compute AI tasks via structured task IDs.
How AI Video & Image Productivity Assistant Works
- The user initiates a request through a chat interface (Feishu, QQ, WeChat) using natural language prompts.
- The assistant utilizes Openclaw Skills to check the availability of the local generation client at http://127.0.0.1:17321.
- The skill maps the user's intent to specific model parameters, such as duration (10s/15s/25s), resolution (HD/1K/4K), and aspect ratio.
- A generation task is submitted to the local engine, which returns a unique task_id immediately to keep the conversation fluid.
- The user can query the status of the task at any time, and once completed, the skill provides a secure, signed URL for the final media output.
AI Video & Image Productivity Assistant Setup
To deploy this skill, ensure your local generation client is active and accessible.
- Install the required Python dependencies:
pip install requests>=2.31.0
- Launch the DYU local client and ensure it is listening on port 17321.
- Verify connectivity within the Openclaw Skills environment by running the check_client function to confirm the local endpoint is responsive.
AI Video & Image Productivity Assistant Data Schema & Taxonomy
The skill organizes media tasks using a structured identification and metadata system to ensure high-fidelity retrieval.
| Attribute | Type | Description |
|---|---|---|
| task_id | String | The unique identifier generated by the local client (e.g., task_xxxxxxxx). |
| model | String | The specific AI model used, such as sora-2-landscape or nano_banana_pro-4K. |
| status | String | Current lifecycle stage: queued, processing, completed, or failed. |
| video_url | String | The primary signed output link for video results, including all signature parameters. |
| metadata | Object | Contains aspect ratio settings and input reference URLs for image-to-media tasks. |
AI Video & Image Productivity Assistant Advanced Features
- Multi-agent batch support: Submit an array of tasks in a single request to maximize local hardware utilization.
- Intelligent parameter mapping: Automatically selects the best model suffix based on user descriptors like 'long video' or 'high definition'.
- Automated task summarization: Generate daily reports on successful and failed generations categorized by model type using Openclaw Skills.
- One-click query generation: Provides users with pre-formatted text blocks to easily track background tasks.
- Secure URL persistence: Ensures that temporary signed URLs from the upstream service are passed through without formatting errors.
SKILL.md
Loading
Related Openclaw Skills
Elderly Care
A comprehensive senior care management skill for home modifications, facility screening, and community service coordination.
Seedance Shot Design
A professional-grade virtual film director skill that transforms vague ideas into production-ready cinematic prompts for Seedance 2.0.
9527 GitHub Trending
A zero-cost automation tool that fetches daily GitHub Trending projects and sends customized notifications to Telegram, DingTalk, or WeChat.
LLM Chat Scraper
A comprehensive scraping utility to extract structured conversation data and citations from leading AI chat platforms via the Scrapeless API.
Comparative Theology & Divine Archetypes
An advanced theological analysis engine that maps the jurisdictions, symbolic functions, and cultural frameworks of deities across global traditions.
Website Change Watcher
A sophisticated AI agent skill designed to monitor websites for meaningful content changes and provide actionable business intelligence reports.
Featured*
