A zero-setup, multi-modal creative media runtime for AI agents to generate images, videos, audio, and 3D assets without requiring provider API keys.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install creative-media
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 creative-media 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 Creative Media?
The creative-media tool is a powerful, unified entry point for AI agents seeking a streamlined creative media pipeline. Operating over the zero-setup Image Skill runtime, it allows agents to perform complex media generation tasks, including image generation, editing, video production, audio creation, and image-to-3D asset generation without needing local servers, complex OAuth flows, or multiple API keys. It offers a single identity, wallet, and billing framework, reducing integration overhead for developers configuring Openclaw Skills.
By standardizing media generation into one thin CLI/API, agents benefit from durable hosted media URLs, recoverable jobs, structured cost receipts, stable JSON outputs, and integrated feedback mechanisms. This eliminates the need to maintain multiple provider accounts or manage complex credential states, allowing you to easily extend the capabilities of your AI agents with the wider library of Openclaw Skills.
Creative Media Use Cases
- Generating high-quality visual, video, audio, or 3D assets dynamically within autonomous agent workflows.
- Performing image editing or modal translations without managing third-party provider accounts or local GPU resources.
- Tracking unified cost receipts, credit balances, and usage metrics across multiple media generation APIs.
- Deploying standardized creative assets to durable, hosted URLs that can be referenced or recovered by future agent executions.
- Incorporating zero-setup media capabilities into customizable Openclaw Skills setups.
How Creative Media Works
- Agent Request Initiation: The AI agent identifies a creative media requirement (such as image generation or editing) and invokes the
creative-mediaintent. - No-Spend Validation: The agent runs an initial guide command with a safe prompt to check current setup parameters and system readiness.
- Runtime Execution: The underlying Image Skill runtime securely processes the generation request using its hosted backend, removing the need for local models.
- Asset Hosting & Tracking: Generated assets are automatically stored, returning durable hosted URLs, stable JSON metadata, and cost receipts to the calling agent.
- Feedback Loop: If the generated output requires adjustments, agents or developers can submit structured feedback directly to the runtime to refine future iterations.
Creative Media Setup
To get started quickly with creative-media using Openclaw Skills, run the initial guide command:
npx -y image-skill@latest create --guide --prompt "a compact field camera on a stainless workbench"
To list available models in a structured JSON format, run:
npx -y image-skill@latest models list --available --json
Install the intent skill to your marketplace environment using the following command:
npx skills add danielgwilson/image-skill-cli --skill creative-media -g -a codex -y
Alternatively, you can install the canonical Image Skill entry:
npx skills add danielgwilson/image-skill-cli --skill image-skill -g -a codex -y
Note: If you have an optional restricted token minted from image-skill signup, it will be saved automatically as IMAGE_SKILL_TOKEN without requiring complex user credentials.
Creative Media Data Schema & Taxonomy
The creative-media skill relies on a unified data structure managed by the shared Image Skill runtime. All outputs are documented and structured to ensure long-term recoverability.
| Data Field | Type | Description |
|---|---|---|
url |
String | Durable, public, and hosted URL pointing to the generated media asset. |
job_id |
String | Unique identifier used to recover, reference, or check the status of a generation job. |
cost |
Object | Detailed financial receipt breakdown representing the usage metrics of the API. |
parameters |
Object | Stable JSON representation of the model settings, prompt details, and parameters used. |
feedback |
Object | Logged system quality feedback sent using the canonical image-skill feedback command. |
Creative Media Advanced Features
- Recoverable Generation Jobs: Retrieve previously generated assets and run histories using historical job IDs to minimize redundant compute spend.
- Cost Receipt Audits: Programmatically review generation pricing, allowing autonomous agents to track wallet budgets before executing resource-heavy media requests.
- Single-Wallet Identity: Manage payment cycles, credits, and model permissions under a single agent identity without dealing with per-provider licensing.
- Multi-Modal Asset Pipeline: Generate, edit, and convert files seamlessly across images, video, audio, and 3D formats through a single CLI abstraction.
- Zero-Setup Fallbacks: Integrate easily into modern multi-agent systems using Openclaw Skills, allowing seamless fallback commands if a specialized capability is lacking.
SKILL.md
Loading
Related Openclaw Skills
ai-chat-enhancer-0f5a92
A consolidated guide and toolset for deploying zero-cost mainstream LLMs on Windows via Chat2API and integrating them into MarginNote.
AI Summary
Automate the extraction and saving of AI-generated insights into your personal or development knowledge base.
AI Video
Automate the collection, structuring, and logging of AI video generation summaries directly into your local knowledge base.
api-tester-dd7739
An AI agent skill designed to guide developers through integrating various AI channels, advanced New API features, and configuring HTTP request nodes.
Image to 3D
A zero-setup, hosted runtime CLI skill that converts 2D images into durable, hosted 3D glb mesh assets without provider credentials.
Requirements Analysis
Helps product and development teams transform ambiguous feature requests into structured, execution-ready requirements documentation.
Featured*
