A unified command-line interface for executing 150+ serverless AI applications across image, video, text, and social media domains.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install inference-sh
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 inference-sh 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 inference-sh?
inference-sh is a comprehensive platform designed to provide developers and AI agents with instant access to a vast library of over 150 AI applications through a streamlined CLI. It eliminates the need for managing individual API integrations or maintaining expensive GPU infrastructure. By utilizing this within the Openclaw Skills ecosystem, developers can programmatically trigger advanced models for image generation, video creation, 3D modeling, and web research.
The skill acts as a bridge to state-of-the-art models like FLUX, Veo, Claude, and Gemini. It is particularly effective for building autonomous workflows where an agent needs to switch between different modalities—such as generating a marketing tweet, creating a matching image, and then upscaling that image—all through a consistent interface and billing model.
inference-sh Use Cases
- Rapidly generating high-quality AI images using FLUX or Gemini 3 Pro.
- Creating cinematic AI videos with Veo 3.1 or Seedance without local hardware.
- Automating social media presence via Twitter/X API integration for posting and engagement.
- Enhancing agent intelligence with multi-source web searches via Tavily and Exa.
- Scaling LLM capabilities by accessing Claude, Kimi, and OpenRouter models through one tool.
How inference-sh Works
- Install the CLI tool on your local machine or server environment.
- Authenticate the session using the login command to link your account.
- Discover available AI applications by searching or filtering through the app list.
- Execute a specific application by providing a JSON input object containing the prompt and parameters.
- Monitor the task status for long-running processes (like video generation) using the unique task ID.
- Retrieve the final output, which is hosted in the cloud or returned directly to the CLI.
inference-sh Setup
To initialize the environment for these Openclaw Skills, install the CLI and sign in:
curl -fsSL https://cli.inference.sh | sh
infsh login
After setup, you can add specific model capabilities to your agent:
npx skills add inference-sh/skills@ai-image-generation
inference-sh Data Schema & Taxonomy
The skill utilizes a structured approach to interact with various AI models. Data is organized as follows:
| Element | Description |
|---|---|
| App Identifier | A string following the provider/model-name format (e.g., google/veo-3-1-fast). |
| Input Schema | A JSON object containing specific parameters like prompt, text, or query. |
| Task Metadata | Tracking information including status, start time, and completion timestamps. |
| Output URI | Direct links to generated media files or structured text results. |
| Sample Generation | Use infsh app sample <app-id> to automatically generate valid input JSON templates. |
inference-sh Advanced Features
- Asynchronous execution using the
--no-waitflag for high-concurrency workflows. - Comprehensive Twitter/X automation suite including following, liking, and direct messaging.
- Specialized utility apps for media merging, video captioning, and background removal.
- Support for any model hosted on OpenRouter, providing an expansive fallback for LLM tasks.
- Multi-agent compatibility via specialized sub-skills for diverse AI tasks.
SKILL.md
Loading
Related Openclaw Skills
Image Upscaling
A comprehensive AI toolkit for upscaling, restoring, and increasing image resolution via high-performance inference models.
Image to Video Conversion
A high-performance guide and toolset for converting static images into dynamic, cinematic videos using state-of-the-art AI motion models.
Google Veo Video Generation
A powerful AI video generation tool leveraging Google Veo models via the inference.sh CLI for high-quality, cinematic output.
FLUX Image Generation
A specialized skill for generating high-quality images using FLUX models by Black Forest Labs via a streamlined CLI interface.
Landing Page Design
A framework for building high-converting landing pages using AI-driven asset generation and proven marketing psychology.
LLM Models via OpenRouter
A powerful CLI-driven skill providing unified access to over 100 leading large language models through OpenRouter integration.
METADATA
Featured*
